Medical image acquisition unit support device

Abstract

The present invention relates to a medical image acquisition unit support device 10, which includes at least one camera 20, a processing unit 30, and an output unit 40. The at least one camera is located near a patient support of the medical image acquisition unit. The at least one camera collects at least one data of a human operator standing next to the patient support. The at least one camera provides the at least one data of the operator to the processing unit. The processing unit determines a height of the operator, the determination including utilizing the at least one data. The output unit outputs a signal for adjusting the height of the patient support. The adjustment including utilizing the height of the operator.

Description

[Technical field]

[0001] The present invention relates to a medical image acquisition unit support device, a medical image acquisition unit support system, a medical image acquisition unit support method, as well as a computer program element and a computer readable medium. [Background technology]

[0002] Patient preparation is an essential and critical component of clinical workflow in medical imaging exams such as MRI, X-ray, CT, attenuated X-ray, and PET. This is because the time required for patient preparation can limit the time slots available for the actual scan. During the exam preparation workflow, the height of the patient support (table) is usually adjusted multiple times to allow for a user-friendly table preparation and also to improve the patient's comfort. This table height adjustment usually needs to be done manually by the operator. This not only increases the exam preparation time but also makes it cumbersome especially when carrying large / heavy objects (e.g. anterior coils) with both hands. Furthermore, the daily work of a medical imaging operator can be stressful and physically demanding due to the complexity of many required tasks and strict time-sensitive requirements. These issues are exacerbated because in most clinical settings, many technicians work with the same medical imaging system, with significant differences in experience and working styles. Summary of the Invention [Problem to be solved by the invention]

[0003] These problems need to be solved. [Means for solving the problem]

[0004] It would be advantageous to provide improved assistance to operators of medical image acquisition units. The object of the invention is solved in the subject matter of the independent claims, further embodiments are incorporated in the dependent claims. It is noted that the aspects and embodiments of the invention described below also apply to a medical image acquisition unit assistance device, a medical image acquisition unit assistance system, a medical image acquisition unit assistance method and a medical imaging method, as well as to a computer program element and a computer readable medium.

[0005] In a first aspect, a medical image acquisition unit support device is provided. The medical image acquisition unit support device includes: At least one camera; A processing unit; and an output unit.

[0006] The at least one camera is located near the patient support of the medical image acquisition unit. The at least one camera collects at least one data of a human operator standing next to the patient support. The at least one camera provides the at least one data of the operator to a processing unit. The processing unit determines a height of the operator. The determination includes utilizing the at least one data. The output unit outputs a signal for adjusting a height of the patient support. The adjustment includes utilizing the height of the operator.

[0007] In this way, the height of the patient support is automatically adjusted to the optimal height for the operator who is preparing the patient on the patient support (e.g. a table) for examination by a medical image acquisition unit such as an MRI, X-ray unit, PET scanner, etc. The operator does not have to do this manually, which frees up the operator's time and allows for a more time-efficient and effective examination.

[0008] In one example, utilizing the at least one datum includes determining a location of the operator within the at least one datum.

[0009] In one example, determining the height of the operator includes determining at least one height at the determined location of the operator.

[0010] Thus, the at least one camera may be a single camera, such as a time-of-flight depth and imaging camera, from which the position of the operator and his / her height can be determined. However, the at least one camera may also be two visible light cameras operating in stereo mode. Images from both cameras may be analyzed to determine depth information and the position of the operator, and the location of the operator may be determined.

[0011] In one example, the at least one camera includes a camera that collects 2D image data, the at least one data includes the 2D image, and the processing unit determines a position of the at least one body part of the operator within the 2D image.

[0012] In one example, the at least one camera includes a camera that collects depth or distance data, and the at least one data includes the depth or distance data, and the processing unit determines a height of the operator based on the depth or distance data at the determined position of the at least one body part of the operator.

[0013] In one example, the at least one body part of the operator includes a top of the operator's head, the operator's neck, and / or the operator's shoulders.

[0014] In one example, a camera that collects depth or distance data is above the patient support.

[0015] In one example, determining the operator's height includes using a known height of a camera to collect depth or distance data above the floor on which the patient support is placed.

[0016] In one example, utilizing the at least one data includes determining an identity of an operator within the at least one data.

[0017] In one example, determining the operator's height includes retrieving the operator's height from a database based on the operator's identity.

[0018] In other words, by identifying the operator, personal information including the operator's height can be extracted from the database, making it possible to appropriately adjust the height of the patient support.

[0019] In one example, the at least one camera includes a camera that collects 2D image data, the at least one data includes the 2D image, and the processing unit is configured to determine an identity of the operator and image analyze the 2D image.

[0020] In one example, the processing unit determines at least one workflow support feature associated with an operation of the medical image acquisition unit by an operator, which includes extracting the at least one workflow support feature from a database based on an identity of the operator. The output unit communicates the at least one workflow support feature to the operator.

[0021] In this way, at least one workflow support feature, such as how to operate a medical image acquisition unit for a particular procedure, can be tailored to the operator. For example, a junior or less experienced operator can be provided with very detailed procedural workflow steps to enable him or her to properly perform the examination. For an experienced operator, this operator can be provided with a much simpler set of support features.

[0022] In a second aspect, a medical image acquisition system is provided, the medical image acquisition system comprising: A medical image acquisition unit; At least one camera; A processing unit; and an output unit.

[0023] The at least one camera is located near the patient support of the medical image acquisition unit. The at least one camera collects at least one data of a human operator standing next to the patient support. The at least one camera provides the at least one data of the operator to a processing unit. The processing unit determines a height of the operator. The determination includes utilizing the at least one data. The output unit outputs a signal for adjusting a height of the patient support. The adjustment includes utilizing the height of the operator.

[0024] In a third aspect, a method for assisting a medical image acquisition unit is provided, the method comprising: collecting, by at least one camera, at least one data of a human operator standing next to the patient support of the medical image acquisition unit; providing at least one data of the operator to a processing unit by at least one camera; determining, by the processing unit, a height of the operator, the determining including utilizing the at least one data; and outputting, by the output unit, a signal for adjusting a height of the patient support, the adjustment including utilizing a height of an operator.

[0025] In another aspect, there is provided a computer program element for controlling one or more of the apparatus and / or systems as described above, which, when executed by a processor, performs a method as described above.

[0026] In another aspect, a computer readable medium having stored thereon the aforementioned program elements is provided.

[0027] The computer program element may for example be a software program, but also an FPGA, a PLD, or any other suitable digital means.

[0028] Advantageously, any advantages gained by any of the above aspects apply to all other aspects as well, and vice versa.

[0029] These aspects and examples will be apparent from and will be elucidated with reference to the embodiments described hereinafter. [Brief description of the drawings]

[0030] Exemplary embodiments are described below with reference to the following drawings:

[0031] [Figure 1] FIG. 1 shows a schematic embodiment of a medical image acquisition unit support device. [Diagram 2] FIG. 2 shows a schematic embodiment of a medical image acquisition unit support system. [Diagram 3] FIG. 3 illustrates a medical image acquisition unit assisted method. [Figure 4] FIG. 4 illustrates an exemplary process for providing medical image acquisition unit support. [Diagram 5] FIG. 5 shows an example of image acquisition and detection of the operator and patient within the image. [Figure 6] FIG. 6 illustrates the process of creating information that uniquely encodes an operator. [Figure 7] FIG. 7 illustrates the process of identifying an operator. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0032] FIG. 1 shows an example of a medical image acquisition unit support device 10. The device includes at least one camera 20, a processing unit 30, and an output unit 40. The at least one camera is located near a patient support of the medical image acquisition unit. The at least one camera collects at least one data of a human operator standing next to the patient support. The at least one camera provides the at least one data of the operator to the processing unit. The processing unit determines a height of the operator. The determination includes utilizing the at least one data. The output unit outputs a signal for adjusting the height of the patient support. The adjustment includes utilizing the height of the operator.

[0033] The device can be retrofitted into an imaging system that includes, for example, a medical image acquisition unit.

[0034] According to one example, utilizing the at least one datum includes determining a location of the operator within the at least one datum.

[0035] According to one example, determining the height of the operator includes determining at least one height at the determined position of the operator.

[0036] According to one example, the at least one camera includes a camera that collects 2D image data, the at least one data includes a 2D image, where the processing unit is capable of determining a position of the at least one body part of the operator within the 2D image.

[0037] According to one example, the at least one camera includes a camera 22 that collects depth or distance data, and the at least one data includes depth or distance data, in which case the processing unit can determine a height of the operator based on the depth or distance data at a determined position of the at least one body part of the operator.

[0038] According to one example, the at least one body part of the operator includes a top of the operator's head, the operator's neck, and / or the operator's shoulders.

[0039] According to one example, a camera that collects depth or distance data is above the patient support.

[0040] According to one example, determining the operator's height includes using a known height of a camera to collect depth or distance data above the floor on which the patient support is placed.

[0041] In one example, the depth or distance data includes at least one distance between the camera and at least one body part of the operator.

[0042] According to one example, utilizing the at least one data includes determining an identity of an operator within the at least one data.

[0043] According to one example, determining the operator's height includes retrieving the operator's height from a database based on the operator's identity.

[0044] According to one example, the at least one camera includes a camera (24) that collects 2D image data, the at least one data includes the 2D image, where the processing unit can determine the identity of the operator and includes image analysis of the 2D image.

[0045] According to one example, the processing unit determines at least one workflow support feature associated with an operation of the medical image acquisition unit by an operator, which includes extracting the at least one workflow support feature from a database based on an identity of the operator, and an output unit communicates the at least one workflow support feature to the operator.

[0046] In one example, a camera that collects the 2D image data is above the patient support.

[0047] FIG. 2 shows an example of a medical image acquisition system 100. The system includes a medical image acquisition unit 110, at least one camera 20, a processing unit 30, and an output unit 40. The at least one camera is located near a patient support of the medical image acquisition unit. The at least one camera collects at least one data of a human operator standing next to the patient support. The at least one camera provides the at least one data of the operator to the processing unit. The processing unit determines a height of the operator. The determination includes utilizing the at least one data. The output unit outputs a signal for adjusting the height of the patient support. The adjustment includes utilizing the height of the operator.

[0048] In one example, utilizing the at least one datum includes determining a location of the operator within the at least one datum.

[0049] In one example, determining the height of the operator includes determining at least one height at the determined location of the operator.

[0050] In one example, the at least one camera includes a camera that collects 2D image data, the at least one data includes a 2D image, in which case the processing unit can determine a position of the at least one body part of the operator within the 2D image.

[0051] In one example, the at least one camera includes a camera that collects depth or distance data, and the at least one data includes depth or distance data, in which case the processing unit can determine a height of the operator based on the depth or distance data at a determined position of the at least one body part of the operator.

[0052] In one example, the at least one body part of the operator includes a top of the operator's head, the operator's neck, and / or the operator's shoulders.

[0053] In one example, a camera that collects depth or distance data is above the patient support.

[0054] In one example, determining the operator's height includes using a known height of a camera to collect depth or distance data above the floor on which the patient support is placed.

[0055] In one example, the depth or distance data includes at least one distance between the camera and at least one body part of the operator.

[0056] In one example, utilizing the at least one data includes determining an identity of an operator within the at least one data.

[0057] In one example, determining the operator's height includes retrieving the operator's height from a database based on the operator's identity.

[0058] In one example, the at least one camera includes a camera that collects 2D image data, and the at least one data includes the 2D image, where the processing unit can determine the identity of the operator and includes image analysis of the 2D image.

[0059] In one example, the processing unit determines at least one workflow support feature associated with an operation of the medical image acquisition unit by an operator, which includes extracting the at least one workflow support feature from a database based on an identity of the operator. The output unit communicates the at least one workflow support feature to the operator.

[0060] In one example, a camera that collects the 2D image data is above the patient support.

[0061] FIG. 3 shows the basic steps of a medical image acquisition unit assisted method 200. The method includes: In a collection step 210, by means of at least one camera, collecting at least one data of a human operator standing next to a patient support of the medical image collection unit; In a providing step 220, providing at least one data of the operator to a processing unit by at least one camera; determining, by the processing unit, a height of the operator, in a determining step 230, the height of the operator including utilizing at least one piece of data; An output step 240 includes outputting, by the output unit, a signal for adjusting a height of the patient support, the adjustment including utilizing a height of the operator.

[0062] In one example, utilizing the at least one datum includes determining a location of the operator within the at least one datum.

[0063] In one example, determining a height of the operator includes determining at least one height at the determined position of the operator.

[0064] In one example, the at least one camera includes a camera that collects 2D image data, and the at least one data includes the 2D image, in which case the method includes determining (225), by the processing unit, a position of the at least one body part of the operator within the 2D image.

[0065] In one example, the at least one camera includes a camera that collects depth or distance data, and the at least one data includes depth or distance data, in which case the method includes determining, by the processing unit, a height of the operator based on the depth or distance data at the determined position of the at least one body part of the operator.

[0066] In one example, the at least one body part of the operator includes a top of the operator's head, the operator's neck, and / or the operator's shoulders.

[0067] In one example, a camera that collects depth or distance data is above the patient support.

[0068] In one example, determining the operator's height includes using a known height of a camera that collects depth or distance data above the floor on which the patient support rests.

[0069] In one example, the depth or distance data includes at least one distance between the camera and at least one body part of the operator.

[0070] In one example, utilizing the at least one data includes determining an identity of an operator within the at least one data.

[0071] In one example, determining the operator's height includes retrieving the operator's height from a database based on the operator's identity.

[0072] In one example, the at least one camera includes a camera that collects 2D image data, and the at least one data includes the 2D image, in which case the method includes determining, by the processing unit, an identity of the operator, which includes image analyzing the 2D image.

[0073] In one example, the method includes determining, by a processing unit, at least one workflow support feature associated with an operation of the medical image acquisition unit by an operator, including extracting the at least one workflow support feature from a database based on an identity of the operator, after which an output unit communicates the at least one workflow support feature to the operator.

[0074] In one example, a camera that collects the 2D image data is above the patient support.

[0075] Therefore, as mentioned above, a new technique has been developed that automatically adjusts the height of the patient support to match the operator's height based on determining the operator's height, making exam preparation faster and more convenient. This new technique allows for automatic identification of the operator to provide personalized features and support that take into account their experience level and working style.

[0076] For example, use a ceiling-mounted image camera (such as an RGB camera - does not need to be ceiling-mounted) and a depth camera (which can be housed within the same camera body). A body landmark detection model tailored to the "RGB" image can be applied to identify key body parts of the operator, such as the head. A corresponding depth sensor can be used to infer the operator's height. This information can then be used to automatically adjust the height of the patient support, enabling fast and convenient exam preparation.

[0077] Another example is for example using a ceiling mounted image camera (e.g. an RGB camera - again, no need to mount on the ceiling). Using a ceiling mounted camera system allows automatic identification of the operator. For person detection in the top view images, dedicated networks can be used, as well as person-encoded convolutional neural networks that can be used to create an encoded operator database. During inference, a database query is made to automatically identify the operator in the collected camera images. This allows the height of the patient support to be adjusted to the height of the operator and other aspects of the workflow support system to be intelligently personalized.

[0078] Therefore, it can accommodate operators of different heights, experience levels, and working styles.

[0079] The medical image acquisition unit support device, the medical image acquisition unit support system, and the medical image acquisition unit support method will be described in further detail with reference to FIGS.

[0080] Figure 4 illustrates an exemplary process for providing medical image acquisition unit assistance. A 2D image sensor, such as an RGB sensor, is shown at 24 and a depth sensor is shown at 22. In the image on the left there is a border around the table indicating the area of ​​the table that is excluded from network processing. The image on the left clearly shows the operator and his head. Head detection is shown at 225 and a small circular marker shown in the image on the right indicates where the operator's head has been determined or detected. An estimation of the operator's height is performed (230) and then a table height adjustment is performed (240).

[0081] Continuing with reference to Figure 4, the images generated by the camera's RGB sensor are first processed by a dedicated neural network trained to detect the operator's body landmarks. To take into account the camera's particular viewpoint, the network training includes a variety of top-view images of a large number of subjects. The creation of such a dataset can be achieved in different ways, by combining / modifying publicly available data sources or by using the ceiling-mounted camera system itself. To avoid patient-induced errors in height estimation, the entire table area (indicated by the box around the table in Figure 4) is excluded from the network processing by assigning a single value to all corresponding pixels.

[0082] In the implementation shown in Figure 4, the network is trained to detect the operator's head. At this position, the image provided by the depth sensor is evaluated to provide an estimate of the distance between the head and the camera. By comparing this distance with the floor depth value, the operator's height can be estimated.

[0083] So, in summary, the new technology is: It consists of a ceiling-mounted RGB / depth camera that provides a continuous data stream of the patient table.

[0084] It does not need to be a continuous stream of image data, and cameras other than RGB cameras can be used, and the RGB and depth cameras do not need to be mounted on the ceiling.

[0085] We use a specialized neural network to detect body landmarks in camera images.

[0086] Image analysis techniques other than neural network-based techniques can be used to identify the position of the operator's head.

[0087] An algorithm is utilized for operator identification and height estimation.

[0088] The algorithm could be to simply subtract the distance from the depth camera to the top of the operator's head from the distance from the camera to the floor.

[0089] Many variations on this process are possible: Additional body landmarks can be used to infer height, such as neck and shoulders. By using a dedicated estimation model that takes 3D landmark coordinates as input and generates a height estimate, we are able to account for changes in the operator's posture while working. By continuously processing the incoming RGB / depth data streams and averaging the results, we can obtain an estimate that becomes more accurate. Instead of a landmark detection model, a customized person segmentation network can be used that provides the outline of the operator. An estimate of the operator's height can then be obtained by taking the minimum depth value within the body outline.

[0090] Images with multiple people in non-table areas can be excluded from the above processing to avoid inaccurate table adjustments due to the patient (usually the patient is taken to patient support together with the operator).

[0091] Once the operator's height is determined, the system adjusts the optimal table height. In a simple implementation, a simple linear model can be used for this purpose. More complex models incorporating the sizes of various body parts (leg, arm, torso lengths) can also be used.

[0092] In more advanced implementations, the table height is automatically adjusted during different stages of preparation for the exam: for example, if the patient's height is known in advance, the height is adjusted so that the patient can sit comfortably on the table, and then the table height is raised to provide an optimal working position for the operator.

[0093] Figure 4 relates to an example where 2D image and depth data are used to determine the height of the operator and allow the height of the patient support (table) to be adjusted. Figures 5-7 relate to an example where depth data is not required and the 2D image itself is used to allow the table height to be appropriately adjusted and other support is provided to the operator.

[0094] For the example described with respect to figures 5 to 7, the new technique consists of two steps: database creation and identification of the operator at inference time. These two steps can be separated in time: the database is created during a (silent) learning phase, in which the operators at a given location are characterized and then the algorithm is activated, realizing the personalization of all learned operators. However, it is also possible to perform these two steps in an interleaved manner: if an operator is detected, the personalization features are activated if this person is found in the database, otherwise the operator is added to the database.

[0095] Figure 5 shows, on the left, an example of an image collected with a 2D imaging camera, such as the RGB camera mentioned above, in preparation for a medical imaging exam, such as an MRI scan, and, on the right, the output of the person detection network shown as an overlay.

[0096] Figure 6 shows an example workflow for creating an operator database. Image regions with operators are cropped and processed by a people encoder such as CNN. The resulting feature vector F is stored in a database. The CNN encoder is denoted by "A", at point "B" the feature vector F is generated and "C" represents the operator database.

[0097] Creating a Database The RGB images received by the ceiling-mounted camera device are automatically processed using a dedicated neural network for person detection. As mentioned above, other 2D image formats may be utilized, machine learning algorithms other than NNs may be utilized, and the camera does not need to be mounted on the ceiling. To account for the specific viewpoint of the camera on the ceiling, the network training includes a variety of top-view images of a large number of subjects. The creation of such a dataset can be achieved in various ways, by combining / modifying publicly available data sources or by using the ceiling-mounted camera system itself. Figure 5 shows an example of an image collected by the camera during preparation for an MRI exam (left) and the network output as an overlay (right).

[0098] To safely identify the operator in such scenes, several criteria are checked, if necessary, on all acquired images: Exactly two people are detected. One of these individuals is in the patient support area. The second individual is located outside the patient support area. If these criteria are met, the second person is identified as the operator.

[0099] The database creation details are shown in Figure 6. An image region around the operator is cropped (e.g., 100x100 pixels) and used as input to a dedicated person-encoder CNN. The goal of this network is to create a feature vector that uniquely encodes the detected operator.

[0100] To achieve this behavior, state-of-the-art CNNs such as VGG [see, e.g., Simonyan, K. and Zisserman, A., 2014. Very deep convolutional networks for large-scale image recognition., arXiv preprint arXiv:1409.1556.] or ResNet [see, e.g., He, K., Zhang, X., Ren, S. and Sun, J., 2016. Deep residual learning for image recognition., In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778] have been trained for person re-identification using customized loss functions such as triplet loss [see, e.g., Hermans, A., Beyer, L. and Leibe, B., 2017. In defense of the triplet loss for person re-identification., arXiv preprint arXiv:1703.07737.]. After training, instead of using the entire CNN, the last fully connected layer (which produces the final output) is truncated and the feature vector F produced by the penultimate layer is used as the person encoding. Note that there are various other approaches to obtaining person encodings with desired properties.

[0101] As long as the above criteria are met, i.e., the operator can be clearly identified, the above processing is performed for every image in the camera data stream. By continuously processing the camera data over a long period of time (e.g., several weeks), a comprehensive database of operator staff is created. Well-known clustering algorithms such as k-means clustering can be used to separate different operators in the database. Pruning and compression techniques can be applied to limit the database size, improving performance during inference.

[0102] Because the person encoding is defined by the CNN weights, it also provides de-personalization of the data, as individual database entries cannot be re-identified as long as access to the CNN is restricted.

[0103] Inference: Identifying operators Once the operator database is created, camera images collected as part of the clinical routine are automatically analyzed, as exemplarily shown in FIG. 7. FIG. 7 shows an example of a workflow during inference. For each detected person, the person encoder CNN processes the corresponding image crop and also performs a database query of the resulting feature vector F1 to determine the person's identity (i.e., operator or patient). From there, the operator's height can be determined, the support table height can be adjusted, and other personalized advice can be provided to the operator regarding the examination. In FIG. 7, "A1" stands for "CNN Encoder", "A2" stands for "CNN Encoder", "B1" stands for feature vector F1, "B2" stands for feature vector F2, "D1" stands for "Database Query", "D2" stands for "Database Query", "E1" stands for "Operator #1", and "E2" stands for "Unknown (=Patient)".

[0104] Continuing with reference to FIG. 7, each camera image is first processed using a person detection network. For each detected person, the corresponding image region is cropped and processed by the person encoder CNN to generate an associated feature vector F i is obtained. If a similar feature vector is found in the database, the operator is identified accordingly. If no match is found, the person is considered unknown.

[0105] Personalization features of a camera-based workflow support system can be manually selected by the operator. Examples of adjustable features include: The height of the operator and the height at which the operator wishes to place the support table if necessary Coil placement guide (e.g., no specific coils shown) Restricting automatic isocenter determination to specific anatomical structures Visual or verbal warnings (collision, body loop, etc.) Automatic reminders to make nurse calls, wear ear protection, etc. Table Speed Table height at various times (e.g., table set low while preparing or cleaning table, table set high when patient is at table) Scanner Touch Screen Layout

[0106] Thus, in summary, this exemplary technique consists of: A ceiling-mounted (or otherwise mounted) RGB camera (or other 2D imaging camera) is used to provide a continuous data stream of the patient table (although it does not have to be a continuous data stream, single frames could be used). It uses a dedicated neural network (or other image processing algorithm) for person detection in camera images. Use a dedicated Convolutional Neural Network (CNN) (or other encoder) for person encoding. Algorithms are used for operator detection, for creating an operator database, and for automatic operator identification during inference.

[0107] Embodiments: For the design and application of new technologies, additional embodiments can be considered: Instead of manually selecting personalization features, operator preferences can be learned automatically based on observed behavior. Examples include manually selected table heights during various exam preparation steps, manually determined isocenter positions despite the availability of automatic features, ignored coil placement guidance, etc. Thus, operators can be automatically detected and identified by the system as described above. However, a new operator not yet present in the database triggers a software routine that automatically "learns" personalized system settings. This routine, in effect, tracks the operator's actions and interprets them as preferences. In this case, such preferences are: Manually selected table heights at various stages of exam preparation can be saved and associated with specific exam events (e.g., setting the table very low during cleaning and setting the table higher during coil placement). Visual features such as coil placement guides are manually enabled / disabled by the user. If the visual layout of the scanner touch screen display is manually changeable, these settings can be saved and automatically relaunched on the next exam.

[0108] If these manual choices were observed repeatedly across different studies, it is highly likely that they correspond to operator preferences.

[0109] In another exemplary embodiment, a computer program or a computer program element is provided, characterized in that it is configured to perform, on a suitable system, the method steps of the method according to one of the above embodiments.

[0110] Thus, the computer program element may be stored in a computing unit that may be part of an embodiment. This computing unit may be configured to execute or direct the execution of the steps of the above-mentioned method. It may furthermore operate the above-mentioned device and / or system components. The computing unit may be configured to operate automatically and / or to execute user instructions. The computer program may be loaded into a working memory of a data processor. The data processor may thus be equipped to execute a method according to one of the above-mentioned embodiments.

[0111] This exemplary embodiment of the invention is directed to both computer programs that use the invention from the beginning and computer programs that, through updates, convert existing programs into programs that use the invention.

[0112] Moreover, the computer program element may provide all the steps required to carry out the procedures of the exemplary embodiments of the methods described above.

[0113] According to a further exemplary embodiment of the present invention a computer readable medium such as a CD-ROM, a USB stick or the like is presented, on which computer program elements are stored, as described in the previous section.

[0114] 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 communication systems.

[0115] However, the computer program may also be presented via 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 invention, a medium making available a computer program element for downloading is provided, the computer program element being configured to perform a method according to one of the aforementioned embodiments of the invention.

[0116] It should be noted that the embodiments of the present invention are described with reference to different subject matters. In particular, some embodiments are described with reference to method type claims, while other embodiments are described with reference to device type claims. However, a person skilled in the art can infer from the above and following description that, unless otherwise specified, any combination of features belonging to one type of subject matter, as well as any combination of features related to different subject matters, are considered to be disclosed in the present application. However, all features can be combined if they provide a synergistic effect that is more than a mere collection of features.

[0117] While the invention has been illustrated and described in detail in the drawings and the foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive. The invention is not limited to the disclosed embodiments. Other variations of 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 dependent claims.

[0118] In the claims, the word "comprising" does not exclude other elements or steps, and the singular elements do not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. 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. Any reference signs in the claims should not be interpreted as limiting the scope.

Claims

1. at least one camera; a processing unit; An output unit; A medical image acquisition unit support device comprising: the at least one camera collects at least one data of a human operator standing next to a patient support of a medical image acquisition unit in the vicinity of the at least one camera; the at least one camera provides the at least one data of the operator to the processing unit; the processing unit determines a height of the operator, the determining including utilizing the at least one piece of data, the utilizing the at least one piece of data including determining an identity of the operator within the at least one piece of data; The output unit outputs a signal for adjusting the height of the patient support, the adjustment including utilizing the height of the operator.

2. The medical image acquisition unit support device of claim 1 , wherein said utilizing said at least one data includes determining a position of said operator within said at least one data.

3. 3. The medical image acquisition unit support device of claim 2, wherein the determining the height of the operator includes determining at least one height of the operator at the determined position.

4. 4. The medical image acquisition unit support device of claim 1, wherein the at least one camera includes a camera that collects 2D image data, the at least one data includes a 2D image, and the processing unit determines a position of at least one body part of the operator within the 2D image.

5. 5. The medical image collection unit support device of claim 4, wherein the at least one camera includes a camera that collects depth or distance data, the at least one data includes depth or distance data, and the processing unit determines the height of the operator based on the depth or distance data at the determined position of the at least one body part of the operator.

6. The medical image acquisition unit support device of claim 5 , wherein the at least one body part of the operator includes an upper portion of the operator's head, a neck of the operator, and / or a shoulder of the operator.

7. The medical image acquisition unit support device of claim 5 , wherein the camera for acquiring depth or distance data is above the patient support.

8. 8. The medical image acquisition unit support device of claim 7, wherein the determining the height of the operator includes utilizing a known height of the camera to collect depth or distance data above a floor on which the patient support rests.

9. The medical image acquisition unit support device of claim 1 , wherein the determining the height of the operator includes retrieving the height of the operator from a database based on the identity of the operator.

10. 4. The medical image acquisition unit support device of claim 1, wherein the at least one camera includes a camera that collects 2D image data, the at least one data includes a 2D image, and the processing unit includes image analysis of the 2D image to determine the identity of the operator.

11. The medical image collection unit support device of claim 1 or 9, wherein the processing unit determines at least one workflow support feature associated with the operation of the medical image collection unit by the operator by extracting at least one workflow support feature from a database based on the identity of the operator, and the output unit communicates the at least one workflow support feature to the operator.

12. a medical image acquisition unit; at least one camera; a processing unit; An output unit; Including, the at least one camera is located near a patient support of the medical image acquisition unit; the at least one camera collects at least one data of a human operator standing next to the patient support; the at least one camera provides the at least one data of the operator to the processing unit; the processing unit determines a height of the operator, the determining including utilizing the at least one piece of data, the utilizing the at least one piece of data including determining an identity of the operator within the at least one piece of data; The output unit outputs a signal for adjusting a height of the patient support, the adjustment including utilizing the height of the operator.

13. collecting, by at least one camera, at least one data of a human operator standing next to the patient support of the medical image acquisition unit; providing the at least one data of the operator to a processing unit by the at least one camera; determining, by the processing unit, a height of the operator, the determining including utilizing the at least one piece of data, and utilizing the at least one piece of data including determining an identity of the operator within the at least one piece of data; outputting, by an output unit, a signal for adjusting a height of the patient support, the adjustment including utilizing the height of the operator; A medical image acquisition unit assistance method, comprising:

14. A computer program for controlling the medical image acquisition unit support device according to any one of claims 1 to 3 and / or the medical image acquisition system according to claim 12, the computer program performing the medical image acquisition unit support method according to claim 13 when executed by a processor.

15. A computer readable medium having stored thereon the computer program of claim 14.

Images