Patient Preparation for Medical Imaging

Abstract

A computer-implemented method for preparing a subject for medical imaging is provided, comprising the steps of: acquiring a series of images of a region of interest including at least a portion of the subject, the series of images including at least a first image and at least a subsequent second image (S10); determining a position of at least one landmark from the series of images, the at least one landmark being anatomically related to a target anatomical structure (S20); determining a confidence level assigned to a position of the at least one landmark (S30); determining a position of the target anatomical structure based on the position of the at least one landmark and the confidence level (S40); and providing the position of the target anatomical structure for preparing the subject for medical imaging (S50).

Description

[Technical Field]

[0001] The present invention relates to medical imaging, and more particularly to a computer-implemented method for preparing a subject for medical imaging, an apparatus for preparing a subject for medical imaging, an imaging system, and a computer program product. [Background technology]

[0002] Medical imaging is a key technology in modern medicine. Medical imaging workflows require trained personnel to operate imaging units, such as magnetic resonance imaging (MRI) systems. Summary of the Invention [Problem to be solved by the invention]

[0003] Preparing the subject and / or imaging unit for medical imaging is time-consuming and critical to the quality of the medical image. Therefore, personnel are challenged with many different tasks. Such tasks include, for example, aligning the subject with the medical imaging unit, positioning the medical imaging device adjacent to the subject, calibrating the imaging unit, and / or documenting the workflow. Each step requires attention from personnel and time. Furthermore, each step can lead to potential errors.

[0004] US Patent Application Publication No. 2018 / 0070904A1 discloses a motion tracking system that overlays tracking data on imaging data of a patient and displays them together. The tracking data is generated by estimating the patient's motion from the data.

[0005] U.S. Patent Application Publication No. 2018 / 116518A1 discloses providing preparatory data for an MRI procedure by using a depth map of a patient on a patient support using a time-of-flight camera.

[0006] Therefore, there may be a need for methods of preparing patients for medical imaging, and in particular for improved methods for preparing patients for medical imaging. [Means for solving the problem]

[0007] The object of the present invention is solved by the subject matter of the independent claims, further embodiments are incorporated in the dependent claims.

[0008] According to a first aspect, there is provided a computer-implemented method for preparing a subject for medical imaging, comprising the steps of: acquiring a series of images of a region of interest comprising at least a portion of the subject, the series of images comprising at least a first image and at least a subsequent second image; determining a position of at least one landmark from the series of images, the at least one landmark being anatomically related to a target anatomy; determining a confidence level assigned to the position of the at least one landmark; determining the position of the target anatomy based on the position and the confidence level of the at least one landmark; and providing the position of the target anatomy for preparing the subject for medical imaging.

[0009] The term subject should be understood broadly in this context and includes any human being and any animal. The term medical imaging should be understood broadly in this context and includes any imaging process configured to image a region of interest, for example, for further use in medical images for examination. Medical imaging can include CT imaging, MRI, and X-ray imaging. Medical imaging can particularly include MRI in this context. A series of images in this context refers to a plurality of single images. The single images can be acquired at specific time intervals. The specific time intervals are related to the frame rate. The frame rate in this context refers to the number of images acquired per second. In this context, the frame rate can be 1, 10, 24, 30, 35, or 60. The images can be acquired by a camera positioned above the subject and / or the medical imaging device so that the acquired images include the region of interest. The camera can also be positioned differently, for example, adjacent to the subject, so that a side view of the region of interest can be obtained. The camera can preferably be a digital optical photo camera or a digital optical video camera. The images can be acquired from one or more cameras. The term "region of interest" in this case should be broadly understood and includes portions of a subject on the subject's surface, such as the torso, back, limbs, and joints, or inside the subject, such as internal organs. For example, the region of interest may be the patella, which is visible from the surface. In another example, the region of interest may be the liver, which is inside the subject and therefore not visible from the field of view of a digital optical camera or digital optical video camera. The region of interest may be obstructed or hidden by, for example, a medical cover, an imaging device (such as an MRI coil), medical assistants, the subject himself (the leg above the desired patella), or human tissue above an organ (such as the liver). The term "position" in this case refers to an x, y, z location in an image, indicating an x, y, z position within an imaging unit and / or imaging system, such as an MRI or CT. This position may also refer to content or extended information of the region of interest in the image. For example, the position may be related to the volumetric dimensions of the liver.The volume dimensions in an image may be related to the volume dimensions and / or location in the coordinate system of an imaging unit or imaging system, such as an MRI, CT, or X-ray system. The term landmark in this case should be broadly understood and refers to a reference point provided by the subject itself. Preferably, the landmark may be a physical marker on the subject's body, such as a bone, head, nose, or rip. The physical marker may be sufficiently concise to be detected in the image. In other words, if the physical marker is visible in the image, it can be easily detected. The term anatomically connected in this case means that a movement or shift of a landmark directly or indirectly affects the position of the target anatomical structure. For example, if the position of the patella changes, the position of the corresponding tibia also changes due to their anatomical connection. In other words, the target anatomical structure and the landmark exhibit a kinematic linkage. For example, the position of an organ such as the liver as the target anatomical structure depends on the position of the adjacent rib, which may be a landmark in this example. The term target anatomical structure in this case refers to a desired anatomical structure whose position must be determined. Examples of target anatomical structures are bones, joints, organs, tissue regions, and blood vessels, but may also be tumors or irregularities detected during previous treatment of the subject. The term confidence level in this case refers to a measure of the certainty of the landmark's location. In other words, the confidence level relates to the reliability of the location. The confidence level can range from 0 to 1, with 0 being associated with low reliability and 1 being associated with high reliability. The confidence level can be estimated based on the entropy or variance of predictions of the location within at least one image. The term "preparing a medical subject" in medical imaging should be broadly understood in this example and includes any tasks related to the medical imaging process, such as positioning the subject on a table, determining a scan position, placing an imaging device on or in the subject, adjusting the controls of the imaging unit or imaging system based on the determined position, or ensuring compliance with safety guidelines. Information about the location of the target anatomical structure can be transmitted to the control unit of the imaging system or imaging unit.Information on the location of the target anatomical structure can be displayed on the screen to guide the medical assistant.

[0010] In other words, the disclosed computer-implemented method for preparing a subject in medical imaging is based on the finding that in medical imaging, it is difficult for a medical assistant to accurately and quickly determine the location of a target anatomical structure of a subject during the preparation phase. Knowledge of the accurate location is important for adapting a medical imaging unit or system. Furthermore, knowledge of the accurate location of the target anatomical structure is important for preparing the subject, such as placing an imaging device on or at the subject. However, a target anatomical structure, such as the liver, may be hidden from the camera. Therefore, the location of the target anatomical structure, such as the liver, cannot be determined directly. Instead, the location of the liver is indirectly determined from adjacent landmarks anatomically related to the target anatomical structure. For example, three landmarks, namely, the head, the fissure, and the lumbar region, are tracked to determine their respective positions, and the liver location is determined based on these positional information. Some reliability issues may arise regarding the location of the three landmarks. For example, a medical assistant may block the view between the camera and the subject's lumbar region. Detecting such reliability issues is important for determining the reliability level of the landmarks. The reliability level of the determination of hidden landmarks in an image may be low. To solve this reliability problem, previous images with a high reliability level for this landmark are used. Therefore, even if there are obstacles in the camera's field of view, it is possible to derive the location of the target anatomical structure with high accuracy and reliability. This increases the productivity of the medical imaging process, since medical assistants do not need to manually perform the task of determining the location of the target anatomical structure. Furthermore, this improves the quality of medical imaging, since the location of the target anatomical structure is accurately calculated by the disclosed method. Determining the location should be understood broadly, and in this case means localization, in particular localization of the landmarks and / or the target anatomical structure.

[0011] According to one embodiment, the location of the target anatomical structure is determined from at least one landmark in the first image if the confidence level of at least one landmark in the second image is below a predetermined threshold. The predetermined threshold can be 0.85, preferably 0.9, and particularly preferably 0.95. In other words, if the current image, which is the most recently available image, provides an insufficient confidence level for the location of at least one landmark, the method does not use the location of the landmark in the current image to determine the location of the target anatomical structure. Instead, the method uses the location of the landmark in the previous image. When the method considers a series of images, it is clear that in the case of several consecutive images with a low confidence level for at least one landmark, the last image with a high confidence level for said at least one landmark is used to determine the location of the target anatomical structure. In other words, the first and second images do not necessarily have to be acquired in direct succession; several images may exist between the first and second images. This can be advantageous because, when the subject is at least partially occluded, the landmarks are corrected by the method, leading to an appropriate determination of the location of the target anatomical structure.

[0012] According to one embodiment, determining the location of the target anatomical structure may further include determining a shift in the location of at least one landmark between the first image and the second image. The term shift in this case refers to a change in the location of at least one landmark between the first image and the second image. The shift in the location of at least one landmark may function as a measure of the inspectability of a determined landmark with a confidence level near a threshold in the second image. Furthermore, the shift may result in a more accurate determination of the location of the target anatomical structure, since possible ambiguity of the location of the landmark in the second image from the location of the landmark in the first image may be eliminated. The shift may further be determined by calculating an average or mean value of the locations in both the first and second images. This may be advantageous for reducing errors occurring during the image acquisition process, since it may smooth out outliers. A shift of two or more landmarks, e.g., five landmarks, may be used to determine a shift in the location of an additional landmark, e.g., a sixth landmark, in the event of occlusion, where the determination is based on the average of the five landmark shifts. This may be advantageous for increasing the localization accuracy of the location of the target anatomical structure.

[0013] According to one embodiment, the location of the target anatomical structure can be determined from the shift in the position of at least one landmark between the first and second images or from at least one landmark in the second image if the confidence level of at least one landmark in the second image exceeds a predetermined threshold. In other words, two possibilities are available for determining the location of the target anatomical structure based on the determined confidence level of at least one landmark in the second image. In the first possibility, the position of at least one landmark is determined based on the shift in the position of at least one landmark between the first and second images, which may be advantageous for correcting / adapting the position of the target anatomical structure from the first image to the second image. The second possibility is to determine the anatomical structure based on the determined landmark in the second image. This may be advantageous in terms of computational efficiency, since only one image is required. The method may further include determining a confidence level of the target anatomical structure for the location of the target anatomical structure. The above-mentioned possibility for determining the location of a landmark in the case of a confidence level exceeding a predetermined threshold may also take into account the confidence level of the location of the target anatomical structure. Both possibilities are feasible, so that the location of the target anatomical structure with the highest confidence level can be selected, which can be advantageous for increasing the accuracy of the localization of the location of the target anatomical structure.

[0014] In one embodiment, based on the determined confidence level, a weighting factor for the shift of the position of at least one landmark can be determined, and the weighting factor is used to determine the position of the target anatomical structure. Determining the shift of the position of the landmark may lead to uncertainty. Therefore, it is useful to take this uncertainty into account by the weighting factor. One possibility is to use the confidence level of the position of at least one landmark in the corresponding image (e.g., from the second image due to the shift from the first image to the second image). This may be advantageous in terms of increasing the accuracy of determining the position of the target anatomical structure.

[0015] In one embodiment, at least one landmark can be selected depending on the presence of the landmark in the series of images. The term "presence" in this case means that the landmark is visible, for example, to a camera mounted above the region of interest. Presence can be obscured by obstacles, for example, medical assistants. The location of the target anatomical structure can be described by a quantity x of 1 to n landmarks, where n is a finite number. To determine the location of the target anatomical structure, the method can select the target anatomical structure at the beginning of the preparation phase simply from the quantity x of visible landmarks. The selection of landmarks can be performed several times during the preparation phase.

[0016] In one embodiment, the target anatomical structure may be obscured by an obstruction. The term obstruction in this case should be understood broadly and includes any component configured to obscure the target anatomical structure. The term may include parts of the subject itself, medical paramedics, medical equipment, etc. In one embodiment, at least one landmark may be obscured by an obstruction.

[0017] In one embodiment, the location of the target anatomical structure can be determined from multiple landmarks, i.e., two or more landmarks. This can be advantageous when one or more landmarks are obscured by obstacles and one or more other landmarks are still visible to the camera. This can be even more advantageous, as more landmarks can result in a more accurate determination of the location of the target anatomical structure. It should be noted that in the case of several landmarks, a corresponding reliability level can also be determined for each landmark, which can be taken into account for determining the target anatomical structure. Furthermore, the above-mentioned possibilities, including shifts and weighting factors, can also be applied in the case of multiple landmarks.

[0018] In one embodiment, determining the location of at least one landmark and determining the location of the target anatomical structure can be based on an image analysis algorithm. The analysis algorithm can include, for example, a segmentation algorithm, an artificial neural network, a deep convolutional neural network, an image acquisition model, and / or a model for determining a confidence level. In one embodiment, the analysis algorithm can use an image acquisition model that describes a process by which a series of images are acquired. The image acquisition model can describe irregularities (e.g., alignment errors, rotation errors) that occur in the imaging process. As a result, the image acquisition model can generate several output images from one input image (e.g., the first image in the series of images) that indicate the irregularities. Based on the several output images, a deep convolutional neural network can determine landmarks in each of the several output images. The uncertainty can then be determined by calculating the entropy between the input image and the several output images. A description of image analysis algorithms that can be used in the embodiments described herein can be found in the document Guotai Wang, Wenqi Li, Michael Aertsen, Jan Deprest, Sebastian Ourselin, Tom Vercauteren, "Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks," Neurocomputing, 2019, https: / / doi.org / 10.1016 / j.neucom.2019.01.103, the contents of which are incorporated herein by reference in their entirety.

[0019] In one embodiment, a control signal for controlling an imaging unit can be derived based on the determined location of the target anatomical structure. The location of the target anatomical structure can be part of the control information of the imaging unit, such as an MRI. This can be advantageous in terms of workflow efficiency, as a medical assistant does not need to perform calculations or related tasks. The method can further automate parts of a medical assistant's workflow.

[0020] In one embodiment, based on the location of the target anatomical structure, guidance data for preparing a subject for medical imaging can be derived, said guidance data including a target alignment of the subject relative to the imaging unit. The term guidance data in this case refers to any data configured to guide a medical assistant to prepare the subject and / or the medical imaging unit for imaging. The guidance data can include a visual representation of a target alignment of a medical device (e.g., a coil) that must be aligned with the subject.

[0021] In one embodiment, determining the location of the target anatomical structure is based on one or more degrees of freedom of one or more joints of the subject. The subject may include joints, bones, tissues, organs, etc. that cannot move completely freely independently of one another. The method may use a cinematic model that includes constraints on the movement of parts of the subject. In particular, the method may take into account the degrees of freedom of the joints. For example, a knee joint can only move within a range of 180°, otherwise the knee joint will fracture. As a result, unrealistic results (e.g., a knee joint angle of 230°) are eliminated, thereby increasing the accuracy of determining the location of the target anatomical structure.

[0022] A further aspect of the present disclosure relates to an apparatus for preparing a subject for medical imaging, the apparatus having: an acquisition unit configured to acquire a series of images of a region of interest comprising at least a portion of the subject, the series of images including at least a first image and a subsequent second image; a first determination unit configured to determine a position of at least one landmark from the series of images, the at least one landmark being anatomically related to a target anatomical structure; a second determination unit configured to determine a confidence level to be assigned to the position of the at least one landmark; a third determination unit configured to determine the position of the target anatomical structure based on the position and the confidence level of the at least one landmark; and a providing unit configured to provide the position of the target anatomical structure for preparing the subject for medical imaging.

[0023] The obtaining unit and / or the determining unit and / or the providing unit may be distributed in separate different hardware units or may be combined into a single hardware unit. The first determining unit, the second determining unit and the third determining unit may be one hardware unit. Furthermore, the obtaining unit and / or the determining unit and / or the providing unit may be virtual units (i.e., software units).

[0024] Optionally, the apparatus may be configured to carry out the method according to the first aspect.

[0025] Another aspect of the present disclosure relates to an imaging system comprising the above-mentioned apparatus, an imaging unit, and an imaging control unit. The imaging unit can be a CT, MRI, or X-ray imaging unit.

[0026] Another aspect of the present disclosure relates to a computer program element that, when executed by a processor, is configured to perform the above-described method and / or to control the above-described apparatus and / or to control the above-described system.

[0027] The computer program element can be stored in a computing unit that can be part of this embodiment. The computing unit can be configured to execute or cause the execution of the steps of the above-described method. The computing unit can further be configured to operate each component of the above-described apparatus. The computing unit can be configured to operate automatically and / or to execute user instructions. The computer program can be loaded into the working memory of a data processor. The data processor can thus be equipped to execute a method according to one of the above-described embodiments. This exemplary embodiment of the present invention encompasses both a computer program that uses the present invention from the beginning and a computer program that, upon updating, transforms an existing program into a program that uses the present invention. Furthermore, the computer program element may be capable of providing all steps necessary to perform the procedures of the exemplary embodiment of the above-described method. According to another exemplary embodiment of the present invention, a computer-readable medium, such as a CD-ROM or a USB stick, is presented, the computer-readable medium having a computer program element stored thereon, the computer program element being described in the previous section. The computer program may be stored and / or 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 telecommunications systems. However, the computer program may also be presented over a network such as the World Wide Web and can be downloaded from such a network into the working memory of a data processor. According to a further exemplary embodiment of the present invention, a medium making a computer program element available for downloading is provided, the computer program element being configured to perform a method according to one of the aforementioned embodiments of the invention.

[0028] It should be noted that the above embodiments may be combined with each other regardless of the aspects involved. Thus, methods may be combined with structural features of devices and / or systems of other aspects, and similarly, devices and systems may be combined with features of each other and with features described above with respect to methods.

[0029] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter.

[0030] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. [Brief explanation of the drawings]

[0031] [Figure 1] FIG. 2 shows an example image of a sequence of images according to a first embodiment of the present disclosure. [Figure 2] 1 shows a diagram of confidence levels across a series of images. [Figure 3] 1 is a schematic diagram of an apparatus according to a first embodiment of the present disclosure. [Figure 4] 1 is a schematic diagram of an apparatus according to another aspect of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0032] FIG. 1 shows an exemplary sequence of images according to a first embodiment of the present disclosure. All four images, 1, 2, 3, and 4, show the same scene, i.e., subject preparation for medical imaging of the patient's right knee, at different stages in time. The images are acquired from a digital optical camera (referred to, for example, in FIG. 4 as acquisition unit 41) mounted above the scene. Specifically, image 1 shows a patient 7 who has just stepped onto a patient support 5. The patient support 5 is part of a magnetic resonance imaging unit 6. The patient support 5 is used to prepare the patient outside the bore 7 of the MRI unit 6. Once the patient 7 is prepared, the patient support 5, along with the patient lying down, is moved into the bore of the MRI unit 6. The medical imaging process then begins to acquire medical MRI images. As can be seen in image 1, not all parts of the patient 7 are visible to the camera; for example, the patient's left foot 8 is hidden by the patient's left knee 9. Image 2 shows a further stage of preparation: the patient 10 is already lying down on the patient support. Image 2 shows a medical assistant 11 holding a coil 12 to be placed on the patient 10. As can be seen in Image 2, nothing obscures the patient 10 during this preparation stage. There are no obstacles between the patient 10 and the mounted camera. Therefore, the camera's view is clear to potential landmarks, such as the right ankle 13, right hip 15, and the target anatomical structure 14, i.e., the knee 14. Landmarks such as the right ankle 13 and right hip 15 are anatomically connected to the target anatomical structure 15, the right knee 15. Therefore, any movement of the landmarks affects the position of the target anatomical structure. For example, if the ankle 13 of the right foot moves laterally to the left, the right knee 15 must also move laterally to the left. In Image 3, the medical assistant has nearly completed the placement of the coil on the patient's right knee. As a result, the right knee is obscured by the coil, and as a result, there is no clear view of the camera to the right knee. The right hip is clearly visible, but the right ankle is also slightly obscured by the coil cable 17. In image 4, the patient support that supports the patient is automatically moved into the MRI bore 16. Therefore, the landmarks and target anatomical structures are also no longer visible to the camera.

[0033] FIG. 2 shows a diagram of confidence levels for a series of images. FIG. 2 corresponds to FIG. 1, where FIG. 1 relates to four images, FIG. 2 relates to 300 images, and the four images in FIG. 1 are a subset of the 300 images in FIG. 2. Confidence levels are plotted on the vertical axis 21 of the diagram. The confidence levels represent the reliability of the determined positions. In this example, confidence levels range from 0 to 1, and decimal values ​​such as 0.81 are possible. The method for determining confidence levels is illustrated in FIG. 3. The horizontal axis 22 of FIG. 2 indicates the number of each image. For each image, the confidence level of the right knee, the ankle of the right foot, or the right hip is plotted as a point on the diagram, respectively. Vertical dashed lines 23, 24, 25, and 26, with numbers 1-4 in parentheses, refer to the respective points on the diagram for images 1-4 in FIG. 1. As can be seen, the confidence levels for the first 50 images have a value of approximately 0 due to the absence of landmarks or target anatomical structures in the images. In the 50-100 image range, the confidence level increases to approximately 0.9. This is due to the increased visibility of the landmarks and target anatomical structures from the first stage of preparing the patient to lie on the patient support to the second stage when the patient is lying on the patient support. In the 120-150 image range, the confidence levels of the right knee and right ankle decrease as the medical assistant places the coil on the patient's right knee. The coil, corresponding cable, and medical assistant obscure the right ankle and right knee, resulting in a decrease in their respective confidence levels. Because the right hip is not obscured by any obstacles during the process, the camera has a free field of view over the right hip. The free field of view over the right hip results in a high confidence level of approximately 0.9. After completing the positioning of the coil on the patient, the confidence levels of the right ankle and right knee increase slightly in the 150-200 image range, but do not reach the previous high confidence level of 0.9 that the right hip has. This is due to the obstruction of the coil and corresponding cable. In the 200-300 image range, the confidence level of both the landmarks and the target anatomical structures decreases as the patient moves with the patient support into the bore and is therefore not visible to the camera. As can be seen from this example, the confidence level of the location of the region of interest decreases for the right knee during preparation, and the confidence level of one landmark, namely the ankle of the right foot, decreases.However, the second landmark, the right hip, remains visible, so the confidence level for the right hip has a high value until the patient moves into the bore.

[0034] 3 is a schematic diagram of a method according to a first aspect of the present disclosure. The computer-implemented method is used to prepare a subject in medical imaging. The subject is a patient in this case. The patient's right knee must be prepared for the MRI process. The right knee is the region of interest in this case. The method has the following steps:

[0035] In a first step S10, a series of images of a region of interest including at least a portion of a subject is acquired, the series of images including at least a first image and at least a subsequent second image. The images are acquired by a digital optical camera mounted above a patient support on which the patient is positioned and prepared for the imaging process. In step S20, the position of at least one landmark is acquired from the series of images, the at least one landmark being anatomically related to a target anatomical structure. The position is acquired by an image analysis algorithm, particularly an algorithm based on a deep neural network. The algorithm further includes an image acquisition model that simulates the process by which the images are acquired. The image acquisition model describes irregularities (e.g., alignment errors, rotation errors) that occur in the imaging process. As a result, the image acquisition model generates several output images showing the irregularities from one acquired input image (e.g., the first image in the series of images). Based on the several output images, a deep convolutional neuron network determines the position of the landmark in each of the several output images. The average of the positions of the landmarks in the several output images then serves as the position of the landmark in the image. In step S30, a confidence level is obtained to assign to the location of at least one landmark. The confidence level may be determined by calculating the entropy between the input image and several output images. Alternatively, the confidence level may be determined by calculating the deviation of the landmark's location in several output images.A description of an image analysis algorithm that can be used for steps S10-S30 described herein is provided in Guotai Wang, Wenqi Li, Michael Aertsen, Jan Deprest, Sebastian Ourselin, Tom Vercauteren, "Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks," Neurocomputing, 2019, https: / / doi.org / 10.1016 / j.neucom.2019.01.103, the contents of which are incorporated herein by reference in their entirety.

[0036] In step S40, the location of the target anatomical structure is determined based on the location of at least one landmark, and a confidence level is determined. For example, in image 3 of FIG. 2, the location and confidence level of the ankle and the location and confidence level of the right hip are used to determine the location of the right knee. Because the confidence level of the ankle is below a predetermined threshold, which is 0.85, the location of the ankle in this image is not used to determine the location of the right knee. Instead, the location of the ankle in image 2 of FIG. 2 is used, and because the confidence level of the location of the right hip in image 3 of FIG. 2 is above the predetermined threshold, the location of the right hip in image 3 of FIG. 2 is used. In other words, if the confidence levels of all the landmarks do not exceed the predetermined threshold, two or more images are used to determine the location of the right knee. In image 2 of FIG. 2, because all the confidence levels of the locations are above the predetermined threshold, only one image is used to determine the location of the right knee. Alternatively, other previous images can be used to determine the location of the right knee. This can be useful to increase the confidence level. Furthermore, it should be noted that in this case, the position of the right knee is also obtained using a neural network, and therefore the confidence level is determined as described above. In other examples or applications, the target anatomical structure is not visible, such as an organ like the liver. The position of the liver must be determined by landmarks and cannot be determined in any other way. In step S50, the position of the target anatomical structure is provided for preparing the subject for medical imaging. Information about the position of the target anatomical structure can be transmitted to a control unit of the imaging system or imaging unit. Information about the position of the target anatomical structure can be displayed on a screen to guide medical assistants.

[0037] 4 is a schematic diagram of an apparatus according to an embodiment of the present disclosure. The apparatus 40 for preparing a subject for medical imaging includes an acquisition unit 41 configured to acquire a series of images including at least a portion of the subject, the series of images including at least a first image and a subsequent second image, a first determination unit 42 configured to determine a position of at least one landmark from the series of images, the at least one landmark being anatomically related to a target anatomical structure, a second determination unit 43 configured to determine a confidence level to be assigned to the position of the at least one landmark, a third determination unit 44 configured to determine the position of the target anatomical structure based on the position and the confidence level of the at least one landmark, and a unit 45 configured to provide the position of the target anatomical structure for preparing a subject for medical imaging. Various aspects of the present invention will be described below. (Appendix 1) 1. A computer-implemented method for preparing a subject in medical imaging, comprising: acquiring a series of images of a region of interest including at least a portion of the subject, the series of images including at least a first image and at least a subsequent second image; determining a location of at least one landmark from the series of images, the at least one landmark being anatomically related to a target anatomical structure; determining a confidence level to be assigned to the location of said at least one landmark; determining a location of the target anatomical structure based on a location of at least one landmark in the series of images and a confidence level across the series of images; providing the location of the target anatomical structure to prepare the subject for the medical imaging; 1. A computer-implemented method comprising: (Appendix 2) 2. The method of claim 1, wherein if the confidence level of the at least one landmark in the second image is below a predetermined threshold, the location of the target anatomical structure is determined from the at least one landmark in the first image. (Appendix 3) 3. The method of claim 1 or 2, wherein determining the position of the target anatomical structure further comprises determining a shift in the position of the at least one landmark between the first image and the second image. (Appendix 4) 4. The method of any one of claims 1 to 3, wherein if the confidence level of the at least one landmark in the second image is above the predetermined threshold, the position of the target anatomical structure is determined from a shift in the position of the at least one landmark between the first image and the second image or from the at least one landmark in the second image. (Appendix 5) 5. The method of any one of claims 1 to 4, wherein a weighting factor for a shift in the position of the at least one landmark is determined based on the determined confidence level, and the weighting factor is used to determine the position of the target anatomical structure. (Appendix 6) 6. The method of any one of claims 1 to 5, wherein the at least one landmark is selected depending on the presence of the landmark in the series of images. (Appendix 7) 7. The method of any one of claims 1 to 6, wherein the target anatomical structure is obscured by an obstacle. (Appendix 8) 8. The method of any one of claims 1 to 7, wherein the location of the target anatomical structure is derived from a plurality of landmarks. (Appendix 9) 9. The method of any one of claims 1 to 8, wherein the step of determining the position of the at least one landmark and determining the position of the target anatomical structure is based on an image analysis algorithm. (Appendix 10) 10. The method of any one of claims 1 to 9, wherein a control signal for controlling an imaging unit is derived based on the determined position of the target anatomical structure. (Appendix 11) 11. A method as described in any one of claims 1 to 10, wherein guidance data for preparing the subject for medical imaging is derived based on the position of the target anatomical structure, the guidance data including target alignment of the subject relative to an image unit. (Appendix 12) 12. The method of any one of claims 1 to 11, wherein determining the position of the target anatomical structure is based on one or more degrees of freedom of one or more joints of the subject. (Appendix 13) 1. An apparatus for preparing a subject in medical imaging, comprising: an acquisition unit configured to acquire a series of images of a region of interest including at least a portion of the subject, the series of images including at least a first image and a subsequent second image; a first determination unit for determining a location of at least one landmark from the series of images, the at least one landmark being anatomically related to a target anatomical structure; a second determination unit for determining a confidence level to be assigned to the location of said at least one landmark; a third determination unit for determining a location of a target anatomical structure based on the location of the at least one landmark in the series of images and the confidence level across the series of images; a providing unit for providing the location of the target anatomical structure to prepare the subject for medical imaging; A device having: (Appendix 14) Apparatus according to claim 13; An imaging unit; An imaging system having an imaging control unit. (Appendix 15) 16. A computer program product configured, when executed by a processor, to perform the method of any one of claims 1 to 12, and / or to control the apparatus of claim 13, and / or to control the imaging system of claim 14. [Explanation of symbols]

[0038] 1,2,3,4 images 5 Patient support 6 Imaging unit 7,10 patients 8 left foot 9 left knee 11 Medical assistants 12 coils 13 Right ankle, landmark 14 Right knee, target anatomy 15 Right lumbar, landmark 16 bore 17 Cable 20 Figure 21 Vertical Axis 22 Horizontal axis 23,24,25,26 Vertical dashed lines 40 equipment 41 Acquisition Units 42 First Decision Unit 43 Second Decision Unit 44 Second Decision Unit 45 units offered

Claims

1. 1. A computer-implemented method for preparing a subject in medical imaging, comprising: acquiring a series of images of a region of interest including at least a portion of the subject, the series of images including at least a first image and at least a subsequent second image; determining a position of at least one landmark from the series of images, the at least one landmark being anatomically connected to a target anatomical structure, the landmark and the target anatomical structure having a kinematic linkage; determining a confidence level to be assigned to the location of said at least one landmark; determining a location of the target anatomical structure based on a location of the at least one landmark in the series of images and the confidence level of the landmark across the series of images; providing the location of the target anatomical structure to prepare the subject for the medical imaging; 1. A computer-implemented method comprising:

2. 2. The method of claim 1, wherein the location of the target anatomical structure is determined from the at least one landmark in the first image if the confidence level of the at least one landmark in the second image is below a predetermined threshold.

3. 3. The method of claim 1, wherein the step of determining the position of the target anatomical structure further comprises determining a shift in the position of the at least one landmark between the first image and the second image.

4. 2. The method of claim 1, wherein the location of the target anatomical structure is determined from a shift in the position of the at least one landmark between the first and second images or from the at least one landmark in the second image if the confidence level of the at least one landmark in the second image is above the predetermined threshold.

5. The method of claim 1 , wherein the at least one landmark is selected depending on the presence of the landmark in the sequence of images.

6. The method of claim 1 , wherein the target anatomical structure is obscured by an obstacle.

7. The method of claim 1 , wherein the location of the target anatomical structure is derived from a plurality of landmarks.

8. The method of claim 1 , wherein the steps of determining the position of the at least one landmark and determining the position of the target anatomical structure are based on image analysis algorithms.

9. The method of claim 1 , wherein a control signal for controlling an imaging unit is derived based on the determined position of the target anatomical structure.

10. 10. The method of claim 1, wherein guidance data for preparing the subject for medical imaging is derived based on the position of the target anatomical structure, the guidance data including a target alignment of the subject relative to an image unit.

11. The method of claim 1 , wherein determining the location of the target anatomical structure is based on one or more degrees of freedom of one or more joints of the subject.

12. 1. An apparatus for preparing a subject in medical imaging, comprising: an acquisition unit configured to acquire a series of images of a region of interest including at least a portion of the subject, the series of images including at least a first image and a subsequent second image; a first determination unit for determining a position of at least one landmark from the series of images, the at least one landmark being anatomically connected to a target anatomical structure, the landmark and the target anatomical structure having a kinematic linkage; a second determination unit for determining a confidence level to be assigned to the location of said at least one landmark; a third determination unit for determining a location of a target anatomical structure based on the location of the at least one landmark in the series of images and the confidence level of the landmark across the series of images; a providing unit for providing the location of the target anatomical structure to prepare the subject for medical imaging; A device having:

13. An apparatus according to claim 12; An imaging unit; An imaging system having an imaging control unit.

14. A computer program product, when executed by a processor, configured to carry out a method according to any one of claims 1 to 11 and / or to control an apparatus according to claim 12 and / or to control an imaging system according to claim 13.

Images