Methods and systems for automated x-ray imaging system orientation using image features

Abstract

A method for predicting an optimal orientation of an imaging device. The method includes obtaining an initial image of an anatomy; extracting at least one image feature of the anatomy from the initial image; and, based on the extracted at least one image feature, predicting an optimal orientation of one or more adjustable components of the imaging device for subsequent imaging of the anatomy. The predicting of the optimal orientation may comprise at least one of: (i) maximizing alignment of the imaging system with the anatomy; (ii) minimizing a region around the anatomy to be excluded from the X-ray imaging; (iii) maximizing alignment of the imaging device to collimate out a portion of the anatomy to be excluded from the subsequent imaging; and (iv) maximizing an amount of the anatomy to be included in the subsequent imaging.

Description

METHODS AND SYSTEMS FOR AUTOMATED X-RAY IMAGING SYSTEM ORIENTATION USING IMAGE FEATURESField of the Disclosure

[0001] The present disclosure is directed generally to methods and systems for predicting an optimal orientation of one or more adjustable components of an imaging system.Background

[0002] Physicians or technicians often need to make several adjustments to an X-ray imaging system in order to capture the desired field of view (FOV) in the image. These adjustments may include both out- of-plane rotation of the X-ray imaging system and in-plane rotation of the X-ray imaging system. As just one example, when gaining radial access, the patient’s arm is extended out at about a 45° angle away from the body, and imaging the radial artery up to the shoulder requires that the imaging system also be rotated to accommodate the rotation of the arm. This rotation may be some combination of rotation of the L-arm, rotation of the detector, and so on. The combination of rotations balances the various needs of the user including aligning the imaging system with the anatomy to be imaged while maintaining the ability to collimate out regions that do not need to be imaged (e.g., air around the arm) or while maximizing the amount of anatomy to be imaged that is included in the FOV (so that only one contrast injection is needed to navigate through the arm and shoulder, for instance). These various evaluations are not always intuitive, can be difficult and time consuming to perform, and can result in an under-utilization of system capabilities (e.g., under-utilization of detector rotation or under-utilization of collimation), suboptimal image acquisition (e.g., smaller FOV than desired requiring a second acquisition with a different FOV), additional usage of contrast (e.g., two DSAs with smaller fields of view instead of one DSA with a larger FOV), and so on. These evaluations may also be further complicated in imaging systems where the source may also rotate independently (e.g., Philips® Azurion® FlexArm, C-less X-ray imaging systems, etc.).Summary of the Disclosure

[0003] There is thus a continued unmet need for methods and systems that efficiently and accurately automatically adjust the orientation of an imaging device (e.g., X-ray imaging device) in order to optimally align the device with the anatomy to be imaged. The imaging device is also referred to herein as an “imaging system” (e.g., “X-ray imaging system” or “X-ray system”).

[0004] Various embodiments and implementations are directed to a method and system for predicting an optimal orientation of one or more adjustable components of an imaging device, using an orientation system. The methods and systems described or otherwise envisioned herein generally relate to in-plane rotations of the imaging / orientation system.

[0005] According to an aspect, a system is provided that is configured to obtain an initial image of an anatomy and extract at least one image feature of the anatomy from the initial image. The system is configured to, based on the extracted at least one image feature, predict an optimal orientation of one or more adjustable components of the imaging device for subsequent imaging of the anatomy. In some embodiments, the one or more adjustable components of the system may then be oriented, automatically or manually, to the predicted optimal orientation.

[0006] According to an aspect, a method is provided for predicting an optimal orientation of an imaging device. The method includes: obtaining an initial image of an anatomy; extracting at least one image feature of the anatomy from the initial image; and, based on the extracted at least one image feature, predicting an optimal orientation of one or more adjustable components of the imaging device for subsequent imaging of the anatomy.

[0007] According to an embodiment, the method includes applying a trained imaging orientation model configured to analyze the extracted at least one image feature to predict the optimal orientation of one or more adjustable components.

[0008] According to an embodiment, the method further includes obtaining information comprising an identification of the anatomy to be imaged by the imaging device and analyzing the information to predict the optimal orientation of the one or more components.

[0009] According to an embodiment, the method further includes receiving, from a user via a user interface, approval to orient the one or more adjustable components to the predicted optimal orientation; and orienting, by the imaging device, the one or more adjustable components to the predicted optimal orientation.

[0010] According to an embodiment, the received approval comprises a fine-tuning, from the user, of the predicted optimal orientation and the orienting comprises orienting the one or more adjustable components to a fine-tuned predicted optimal orientation.

[0011] According to an embodiment, the predicting of the optimal orientation of the one or more adjustable components comprises at least one of: (i) maximizing alignment of the imaging device with the anatomy; (ii) minimizing a region around the anatomy to be excluded from the subsequent imaging; (iii) maximizing alignment of the imaging device to collimate out a portion of the anatomy to be excluded fromthe subsequent imaging; and (iv) maximizing an amount of the anatomy to be included in the subsequent imaging.

[0012] According to an embodiment, the method further includes providing, via a user interface, the predicted optimal orientation of one or more adjustable components to a user as instructions to orient the one or more adjustable components to the optimal orientation or to request approval to orient, by the imaging device, the one or more adjustable components to the predicted optimal orientation, or automatically orienting, by the imaging device, the one or more adjustable components to the predicted optimal orientation.

[0013] According to an embodiment, providing, via a user interface, the predicted optimal orientation of one or more adjustable components to a user comprises providing a predicted image of the anatomy if the one or more adjustable components are adjusted to the predicted optimal orientation.

[0014] According to an embodiment, providing, via a user interface, the predicted optimal orientation of the one or more adjustable components comprises providing a visual display of the optimal orientation of the one or more adjustable components.

[0015] According to another aspect, a system for predicting an optimal orientation of an imaging device is provided. The system includes an imaging device comprising one or more adjustable components and configured to obtain the initial image and perform the subsequent imaging; and a processor configured to predict, based on the initial image, an optimal orientation of the one or more adjustable components for subsequent imaging of the anatomy.

[0016] According to an embodiment, the system further includes the processor configured to apply a trained imaging orientation model configured to analyze the initial image of the anatomy to predict the optimal orientation of the one or more adjustable components.

[0017] According to an embodiment, the processor is further configured to automatically orient the one or more adjustable components to the predicted optimal orientation.

[0018] According to an embodiment, prediction of the optimal orientation comprises one of at least one of: (i) maximize alignment of the imaging device with the anatomy; (ii) minimize a region around the anatomy to be excluded from the subsequent imaging; (iii) maximize alignment of the imaging device to collimate out a portion of the anatomy to be excluded from the subsequent imaging; and (iv) maximize an amount of the anatomy to be included in the subsequent imaging.

[0019] According to an embodiment, the system further includes a user interface configured to provide, to a user, the predicted optimal orientation of the one or more adjustable components.

[0020] According to an embodiment, providing the predicted optimal orientation of the one or more adjustable components comprises at least one of: (i) providing a predicted image of the anatomy if the oneor more adjustable components are adjusted to the predicted optimal orientation; and (ii) providing a visual display of the optimal orientation of one or more adjustable components.

[0021] According to another aspect, a non-transitory computer-readable storage medium is provided. The non-transitory computer-readable storage medium has stored a computer program that includes instructions which, when executed by a processor, cause the processor to obtain an initial image of an anatomy; extract at least one image feature of the anatomy from the initial image; and, based on the extracted at least one image feature, predict an optimal orientation of one or more adjustable components of the imaging device for subsequent imaging of the anatomy. In some embodiments, the one or more adjustable components of the system may then be oriented, automatically or manually, to the predicted optimal orientation.

[0022] It should be appreciated that all combinations of the foregoing concepts and additional concepts discussed in greater detail below (provided such concepts are not mutually inconsistent) are contemplated as being part of the inventive subject matter disclosed herein. In particular, all combinations of claimed subject matter appearing at the end of this disclosure are contemplated as being part of the inventive subject matter disclosed herein. It should also be appreciated that terminology explicitly employed herein that also may appear in any disclosure incorporated by reference should be accorded a meaning most consistent with the particular concepts disclosed herein.

[0023] These and other aspects of the various embodiments will be apparent from and elucidated with reference to the embodiment(s) described hereinafter.Brief Description of the Drawings

[0024] In the drawings, like reference characters generally refer to the same parts throughout the different views. The figures showing features and ways of implementing various embodiments and are not to be construed as being limiting to other possible embodiments falling within the scope of the attached claims. Also, the drawings are not necessarily to scale, emphasis instead generally being placed upon illustrating the principles of the various embodiments.

[0025] FIG. 1 is a flowchart of a method for predicting an optimal orientation of one or more adjustable components of an X-ray system, in accordance with an embodiment.

[0026] FIG. 2 is a schematic representation of an orientation X-ray system, in accordance with an embodiment.

[0027] FIG. 3A is a fluoroscopy image acquired by an interventional X-ray imaging system, in accordance with an embodiment.

[0028] FIG. 3B is an RGB image acquired by an optical camera, in accordance with an embodiment.

[0029] FIG. 4 is a flowchart of a method for training an X-ray orientation model, in accordance with an embodiment.

[0030] FIG. 5A is a schematic representation of an X-ray orientation system providing an optimal orientation of an X-ray source (Rsand X-ray detector (RD) together, in accordance with an embodiment.

[0031] FIG. 5B is a schematic representation of an X-ray orientation system providing an optimal orientation of an L-arm (RL) followed by providing an optimal orientation of the detector ( / ?D). in accordance with an embodiment.

[0032] FIG. 6 is a schematic representation of a slider of an X-ray orientation system, in accordance with an embodiment.Detailed Description of Embodiments

[0033] The present disclosure describes various embodiments of a system and method configured to predict an optimal orientation of one or more adjustable components of an imaging system (e.g., X-ray system). More generally, Applicant has recognized and appreciated that it would be beneficial to provide a method and system to efficiently optimize X-ray image acquisition (or acquisition of other imaging modalities). An X-ray orientation system obtains an initial image of a subject’s anatomy, and extracts at least one image feature of the subject’s anatomy from the initial image. The X-ray orientation system analyzes the extracted image feature(s) to predict an optimal orientation of one or more adjustable components of the X-ray system, where the optimal orientation optimizes one or more aspects of X-ray imaging for subsequent imaging of the subject’s anatomy by the X-ray system. The one or more adjustable components of the system may then be oriented, automatically or manually, to the predicted optimal orientation.

[0034] The embodiments and implementations disclosed or otherwise envisioned herein may be utilized with any system that may utilize or benefit from optimizing orientation of imaging components. For example, one application of the embodiments and implementations disclosed or otherwise envisioned herein is X-ray imaging, such as during routine imaging, catheterization, and many other patient procedures. One application is to improve the functionality of the Philips® Azurion® or Zenition® imaging system and software (manufactured by Koninklijke Philips, N.V.), among other products. However, the disclosure isnot limited to these devices or systems, and thus disclosure and embodiments disclosed herein can encompass any system that may utilize or benefit from optimizing orientation of imaging components.

[0035] Referring to FIG. 1, in one embodiment, is a flowchart of a method 100 for predicting an optimal orientation of one or more adjustable components of an X-ray system, using an X-ray orientation system. The methods described in connection with the figures are provided as examples only, and shall be understood not to limit the scope of the disclosure. The X-ray orientation system can be any of the systems described or otherwise envisioned herein. The X-ray orientation system can be a single system or multiple different systems.

[0036] At step 110 of the method, an X-ray orientation system 200 is provided. Referring to an embodiment of an X-ray orientation system 200 as depicted in FIG. 2, for example, the system comprises one or more of a processor 220, memory 230, user interface 240, communications interface 250, and storage 260, interconnected via one or more system buses 212. It will be understood that FIG. 2 constitutes, in some respects, an abstraction and that the actual organization of the components of the system 200 may be different and more complex than illustrated. Additionally, X-ray orientation system 200 can be any of the systems described or otherwise envisioned herein. Other elements and components of the X-ray orientation system 200 are disclosed and / or envisioned elsewhere herein.

[0037] According to an embodiment, the X-ray orientation system 200 comprises or is in direct or indirect communication with an X-ray system or device 270. The X-ray system or device 270 can be any system or device configured to obtain X-ray imaging of a patient, such as a human being or an animal, among other targets. The X-ray system or device 270 may be a fixed system or a mobile system. According to an embodiment, the X-ray system or device 270 comprises one or more adjustable components, where the one or more adjustable components may be adjusted to achieve a goal of X-ray imaging as described or otherwise envisioned herein. For example, a fixed monoplane / biplane C-arm X-ray imaging system may comprise one or multiple adjustable components, such as adjustment (rotation, etc.) of an L-arm of the device, and / or adjustment (rotation, etc.) of a detector of the system. The imaging system may alternatively be a mobile C-arm X-ray imaging system or a C-less X-ray imaging system, with adjustment components. The X-ray system may comprise other adjustable components.

[0038] According to an embodiment, the X-ray orientation system 200 comprises or is in direct or indirect communication with an electronic medical record system and / or an electronic medical records (EMR) database 280 from which the information about patients, including demographic, diagnosis, and / or treatment information, may be obtained or received. For example, EMR database may comprise information about an imaging or treatment procedure for a patient, including the anatomy that will be imaged during the procedure. According to an embodiment, the electronic medical record system 280 may be a local orremote database and is in direct and / or indirect communication with system 200. Thus, according to an embodiment, the system comprises an electronic medical record database or system 280.

[0039] At optional step 120 of the method, the X-ray orientation system 200 receives or obtains information that may include an identification of a subject’s anatomy to be imaged by the X-ray system, which can be utilized by downstream steps of the system to properly orient the one or more adjustable components of the system as described or otherwise envisioned herein. The information can be received from electronic medical record database or system 280. Alternatively, the information can be received via a user interface or other input from a physician or technician. As another alternative, the information can be extracted from an image taken of the patient. In some cases, the received information may include more than just the identification of a subject’s anatomy to be imaged by the X-ray system, including demographic information, treatment information, diagnosis, and / or other information. Once received, the information may be utilized immediately, and / or it may be temporarily or permanently stored in local and / or remote memory for future use.

[0040] At step 130 of the method, the X-ray orientation system 200 receives or obtains one or more images of a patient. According to an embodiment, the one or more images are X-ray images received from the X-ray device or system 270, taken of the patient at the beginning of, or during, an imaging session or procedure . However, according to other embodiments, the one or more images might be obtained by another imaging modality, as long as the image is sufficient for use in downstream steps of the method as described or otherwise envisioned herein.

[0041] For example, referring to FIGS. 3 A and 3B in one embodiment, one or more images of the patient can be obtained by an imaging modality for optimization of subsequent imaging by the X-ray orientation system. In FIG. 3 A, the initial image is a fluoroscopy image acquired by an interventional X- ray imaging system such as Philips Azurion or Zenition among many other possible X-ray systems. In FIG. 3B, the initial image is an RGB image acquired by an optical camera such as Philips ClarifEye® (manufactured by Koninklijke Philips, N.V.), where an optical camera might be mounted on the interventional imaging system, among many other possible optical cameras. Other imaging modalities are possible.

[0042] Once obtained, the one or more initial images of the patient can be utilized immediately, and / or it may be temporarily or permanently stored in local and / or remote memory for future use, including for use as training data.

[0043] At step 140 of the method, the X-ray orientation system 200 extracts one or more image features regarding the subject’s anatomy from the received one or more initial images. The X-ray orientation systemwill utilize the extracted one or more image features to predict an optimal orientation of the one or more adjustable components, and thus the one or more extracted image features can be any feature suitable for use by the X-ray orientation system for optimal orientation prediction. According to an embodiment, the feature may be information regarding a bony structure in a fluoroscopy image, external anatomy from an RGB image, or any other usable image feature. The relevant one or more image features can be extracted from the one or more initial input images using any feature extraction method, including but not limited to feature extractors such as scale-invariant feature transform (SIFT) or speeded up robust features (SURF), edge extractors such as Canny edge detector or Hough transform, and many others. Alternatively, the relevant one or more image features can be extracted from the one or more initial input images using deep learning based feature extractors. Other methods of feature extraction are possible.

[0044] Once extracted, the one or more extracted image features can be utilized immediately, and / or it may be temporarily or permanently stored in local and / or remote memory for future use, including for use as training data.

[0045] At step 150 of the method, the X-ray orientation system analyzes the extracted at least one image feature to determine or predict an optimal orientation of one or more adjustable components of the X-ray system. The X-ray orientation system can analyze the image feature in a variety of different ways to predict or determine an optimal orientation of one or more adjustable components of the X-ray system. For example, a processor of the X-ray orientation system may be programmed to receive and analyze the extracted image feature to identify or determine an angle or location of an anatomical structure within the initial image, and then use this identified or determined angle or location to re-orient an adjustable component of the X-ray system such that the structure within the initial image is captured with an optimal orientation of the X-ray system in subsequent images. Thus, the subsequent images obtained by the X-ray system will comprise a different view of the anatomical structure within the image.

[0046] According to an embodiment, this optimal orientation of the one or more adjustable components of the X-ray system depends upon one or more factors. For example, the optimal orientation may be one that optimizes one or more aspects of X-ray imaging for subsequent imaging of the subject’s anatomy by the X-ray system. These aspects of X-ray imaging may be, for example, one or more of: (i) maximizing alignment of the X-ray imaging system with the subject’s anatomy, (ii) minimizing a region around the subject’s anatomy that is preferably excluded from the X-ray imaging, such that this region is minimized and the subject’s anatomy is maximized; (iii) maximizing alignment of the X-ray imaging system to collimate out anatomy to be excluded from X-ray imaging (such as maximizing collimation shutter alignment, among other alignments); and (iv) maximizing an amount of the subject’s anatomy to be included in the X-ray imaging, among other aspects. Notably, achieving one aspect may simultaneouslyachieve another aspect. These aspects do not need to be satisfied in every imaging procedure or situation. For instance, in some situations (e.g., during a treatment delivery phase of a procedure), only a small region of interest may need to be included in the field of view (FOC). The X-ray orientation system may be programmed or designed to know what aspects or balance of aspects are necessary for a patient, during a phase of a procedure, during imaging of a particular anatomy, and / or at other points or times, and can thus orient the one or more adjustable components of the X-ray system pursuant to those aspects or balance of aspects. Accordingly, the optimal orientation of the system at one timepoint during a procedure may be different than at another timepoint for the same procedure. Similarly, the optimal orientation of the system for one patient may be different than for another patient. Many other variations are possible.

[0047] According to an embodiment, the X-ray orientation system analyzes the extracted at least one image feature to predict an optimal orientation of one or more adjustable components of the X-ray system, and further includes within that analysis the information received from the EMR database or system 280, or other source such as via a user interface or other input from a physician or technician, about the patient. For example, this information may include demographic information, treatment information, diagnosis, and / or other information. Thus, received information such as information about the procedure to be performed, the weight or age of the patient, and other information could be informative when the system is determining the optimal orientation of the patient. Procedural information could inform the system regarding the structure(s) for which to maximize imagery, optimal orientation of the X-ray machine relative to the anatomy, and other beneficial information. Patient information such as weight or age of the patient could be relevant to the size of the patient for example, and thus could inform the system about an optimal orientation of the X-ray machine relative to the anatomy, among other beneficial information.

[0048] According to an embodiment, the X-ray orientation system uses a trained X-ray orientation model to analyze the extracted at least one image feature (as input to the model) to predict an optimal orientation of one or more adjustable components of the X-ray system (as output of the model). The trained X-ray orientation model can be any model that can be trained to utilize the input to generate the output, as described or otherwise envisioned herein. For example, the trained X-ray orientation model can be a neural network or other trained machine learning model. Thus, according to an embodiment, the X-ray orientation system comprises a trained X-ray orientation model that receives the input data and outputs an optimal orientation of the various one or more orientable parts of the X-ray imaging system such that an appropriate FOV of the region of interest (ROI) is imaged.

[0049] The X-ray orientation model can be trained in a variety of different ways. According to one embodiment, the X-ray orientation model is trained in an unsupervised manner by designing loss functionsthat capture some or all of the user needs. That is, the model is trained to optimize or achieve one or more target aspects of the X-ray system, procedure, and / or imaging session.

[0050] According to one embodiment, as with a radial access case for example, one or more relevant image features may be extracted from the one or more initial input images (e.g., bony structure(s) in fluoroscopy images, the arm in RGB images) and loss functions may be formulated. For example, a loss function can be formulated where the following:Li = cos(0) (Eq. 1) is minimized. Here, 6 represents the angle between the vector representing the principal component of the extracted feature(s) and the vector parallel to the y-axis. The principal component is the vector pointing in the direction that maximizes the variance in the extracted feature set and can be computed using known methods such as principal component analysis. Orientating the various orientable parts of the X-ray imaging system to minimize 1^ aligns the relevant image features with the y-axis so that relevant image features are also aligned with collimators, maximizing the ability to collimate out air or other undesirable or unnecessary areas around the target ROI.

[0051] As another example, a loss function can be formulated where the following:L2= cos(< >) (Eq. 2) is minimized. Here, (p represents the angle between the vector representing the principal component of the extracted feature(s) and the vector representing the diagonal axis through the image space. Orienting the various orientable parts of the X-ray imaging system to minimize L2aligns the relevant image features with the diagonal axis so that the amount of relevant image features included in the FOV is maximized, reducing the need for additional acquisitions, and so on. Such an alignment would be optimal for elongated features such as long thin bony structures, long thin vascular structures, and so on

[0052] According to another embodiment, the X-ray orientation model is trained in a supervised manner. In this embodiment, the optimal orientation of the one or more adjustable components of the X- ray system may be configured to minimize the difference between a ground truth or gold standard image or angle, and the image or angle identified in the initial image via the extracted image feature (s). A ground truth or gold standard may be available either in the form of what a final generated image should look like or in the form of an ideal orientation of each of the one or more adjustable components of the imaging system. The optimization may, therefore, minimize the difference between the predicted image and the ground truth or gold standard image, and / or minimize the difference in an angle found in the predicted orientation and an angle found in the ground truth or gold standard orientation. The angles found in the predicted and ground truth / gold standard orientation may be, for example, the angles of the principalcomponents of the extracted feature(s) in the predicted and ground truth / gold standard images, respectively. Alternatively, the angles may represent the angles of the various orientable components of the X-ray system that generate the predicted and ground truth / gold standard images, respectively.

[0053] This is not an exhaustive list of loss functions, or other formulations, that may be utilized to analyze the extracted image features and generate information used to determine or predict an optimal orientation of the one or more adjustable components of the X-ray system.

[0054] According to an embodiment, the orientations of the various orientable or adjustable components of the X-ray system may be optimized together, depending on the scenario. For instance, in the case of a C-less system, the orientation of the X-ray source and X-ray detector may be optimized at the same time. Referring to FIG. 5A, in one embodiment, the trained X-ray orientation model can provide an optimal orientation of the X-ray source (Rsand X-ray detector (RD) together. Similarly, the X-ray orientation model can provide the post-processing transformation to be applied to the acquired image (Rp). The trained X-ray orientation model may be, for example, a trained neural network (NN).

[0055] According to another embodiment, the orientations of the various orientable or adjustable components of the X-ray system may be optimized separately or individually. For instance, in the case of a C-arm system, the orientation of the L-arm may be optimized first by minimizing Li (see Eq. 1 above), and once the optimal orientation of the L-arm is found and fixed, the orientation of the detector may be optimized, if needed, by minimizing L2(see Eq. 2, above). Referring to FIG. 5B, in one embodiment, the trained X-ray orientation model (neural network NNi) can determine the optimal orientation of the L-arm (RL) as described or otherwise envisioned herein, and then the trained X-ray orientation model (neural network NN2) can determine the optimal orientation of the detector (RD) as described or otherwise envisioned herein. Notably, neural network NNi and neural network NN2 can be the same neural network or a single trained X-ray orientation model, configured to perform both orientation predictions or determinations. According to another embodiment, neural network NNi and neural network NN2 can be different neural networks or different trained X-ray orientation models, each trained individually to perform the specific associated orientation prediction.

[0056] The trained X-ray orientation model may be of any type including a convolutional neural network (CNN) or a transformer network or other neural network. For instance, the neural network may be a CNN that is trained to regress the orientation of the various orientable parts of the system, by estimating the orientation of the various orientable parts of the system, generating a corresponding transformed image that would result from the new orientation of the system, and computing the appropriate loss function to evaluate whether the appropriate system orientation is achieved. During training, the value of the lossfunction, which may be computed using functions such as the mean absolute error (MAE), mean squared error (MSE), and so on, is typically minimized. Various methods are known for solving loss minimization problems, such as stochastic gradient descent (SGD), adaptive moment estimation (Adam), and so on, that compute the derivative of the loss function with respect to model parameters. These derivatives inform the algorithm how the model parameters must be adjusted in order to minimize the loss function. These steps of estimating the orientation, generating the corresponding transformed image, computing the loss functions, and updating the model parameters are repeated several times during training until the model’s parameters generate outputs that result in small loss function values.

[0057] Referring to FIG. 4, in one embodiment, is a flowchart of a method 400 for training the X-ray orientation model of the X-ray orientation system 200. This method may be performed by the X-ray orientation system, or may be performed by another system such as a specialized machine learning model training system.

[0058] At step 410 of the method, the training system receives training data which will be used to train the model. The training data can be any data sufficient to train the model to utilize the described input data to generate the described output. For example, the training data may comprise X-ray images for each of a plurality of patients and procedures, including images before and after optimization, including with ground truth optimization. In some orientations, the training data may include X-ray images that identify different structures (e.g., bony structures or vascular structures) in anatomies of the plurality of patients and corresponding ground truth optimal orientations of one or more adjustable imaging components for (i) maximizing alignment of the imaging device with the anatomies; (ii) minimizing a region around the anatomies to be excluded from imaging; (iii) maximizing alignment of the imaging device to collimate out a portion of the anatomies to be excluded from imaging; and / or (iv) maximizing an amount of the anatomies to be included from imaging. For example, in a supervised learning context, the structures and structures (e.g., bony structures or vascular structures) and such corresponding optimal orientations for imaging the anatomies with the structures may be annotated in the training data for the training of the model. This training data, which could be utilized in a supervised or unsupervised manner, can comprise X-ray imaging for 100s or 1000s of patients and / or procedures, and can be updated with new imaging. The training data may also comprise other information. This training data may be obtained and curated by an expert such as a clinician, or it may be obtained and curated under the supervision of a clinician, or it may be obtained and utilized without curation. The training data may be received from any source. For example, the training data may be received from the electronic medical record database or system 280, or any other component of the X-ray orientation system or a training system. According to an embodiment, the X-ray orientationsystem 200 comprises or is in direct or indirect communication with an imaging database which comprises some or all of the training data set.

[0059] According to an embodiment, the training system may comprise a data pre-processor or similar component or algorithm configured to process the received training data. For example, the data preprocessor analyzes the training data to remove noise, bias, errors, and other potential issues. The data preprocessor may also analyze the input data to remove low quality data. Many other forms of data preprocessing or data point identification and / or extraction are possible.

[0060] At step 420 of the method, the training system trains the X-ray orientation model, using the training data, to determine from input data an optimal orientation of one or more adjustable components of an X-ray system. For example, in some embodiments, the trained model may determine, from an input image of an anatomy, a particular bony or vascular structure in the anatomy and, based on that particular structure, predict the optimal orientation of the one or more adjustable components to image the anatomy. The X-ray orientation model is trained using any method for training such a model. The trained X-ray orientation model is a unique model based on the training data used to train the model. Following training, the system comprises a trained X-ray orientation model.

[0061] Thus, following training, the X-ray orientation model is a specialized model configured to receive the specialized input (namely, the one or more image features extracted from the initial image of the patient) and generate the very specific output, namely the predicted optimal orientation of the one or more adjustable components of the X-ray system, where optimal optimizes or achieves one or more target aspects of the X-ray system, procedure, and / or imaging session. Alternatively, in the case that the X-ray orientation model is a neural network, the model may be configured to receive the specialized input of the initial image of the patient, which may be pre-processed, and extract the relevant image features using the layers of the neural network.

[0062] At step 430 of the method, the trained X-ray orientation model is stored for future use. According to an embodiment, the trained X-ray orientation model may be stored in local or remote storage.

[0063] Returning to method 100 in FIG. 1, at step 160 of the method, the X-ray orientation system utilizes the predicted optimal orientation of one or more adjustable components of the X-ray system generated in step 150. The X-ray orientation system can utilize the predicted optimal orientation in a wide variety of ways.

[0064] According to an embodiment, at step 160 of the method, the X-ray orientation system can itself automatically orient the one or more adjustable components of the system to the predicted optimal orientation. Thus, the X-ray orientation system can be programmed or designed or otherwise configuredsuch that it automatically responds to an optimal orientation prediction by orienting the one or more adjustable components of the system to the predicted optimal orientation. Accordingly, the one or more adjustable components of the system can comprise machinery allowing the component to be automatically adjusted. Motors, servos, or other components can provide this automated functionality.

[0065] According to another embodiment, the system may fine-tune the one or more adjustable components of the system using new images acquired from its updated orientation. For example, when optimizing the detector orientation, the system may compare a vector representing the principal component of the extracted feature(s) from the new image and a vector representing a diagonal through the image space, and can then perform a few steps of optimization in order to further minimize the angle between the two vectors. This can be an automated process, and is useful in cases where the first predicted optimal orientation may not have been accurate (due to noise or other artifacts in the image) or in cases where the patient moves or is moved after the first image is acquired and the predicted optimal orientation is outdated.

[0066] According to another embodiment, at step 160 of the method, the X-ray orientation system provides the predicted optimal orientation of one or more adjustable components of the X-ray system to a user via a user interface of the system. The user interface may be any display or interface that enables display of the predicted optimal orientation, in text, visual, or other format.

[0067] The predicted optimal orientation of one or more adjustable components of the X-ray system may be provided via the user interface in a variety of different ways. According to an embodiment, the predicted optimal orientation of one or more adjustable components of the X-ray system are provided to a user as instructions to orient the one or more adjustable components to the optimal orientation.

[0068] According to another embodiment, the predicted optimal orientation of one or more adjustable components of the X-ray system are provided to a user as a request for approval to orient, by the X-ray system, the one or more adjustable components to the predicted optimal orientation. Thus, at step 170 of the method, the system may receive, from the user via the user interface, approval to orient the one or more adjustable components to the predicted optimal orientation. And at step 180 of the method, after receiving that approval, the X-ray system may orient the one or more adjustable components to the predicted optimal orientation.

[0069] According to another embodiment, the predicted optimal orientation of one or more adjustable components of the X-ray system are provide to a user along with a preview of the corresponding image that will be generated from the suggested optimal orientation of the imaging system. The transformations (e.g., rotations) that must be applied to the one or more adjustable components of the X-ray system in order to move them to the predicted optimal orientation may be applied to the input image in order to generate thepreview. This may be performed as a post-processing step. Alternatively, the transformations may be applied by the X-ray orientation model. Thus, the X-ray orientation model can be further trained to generate a predicted X-ray image that is predicted to result from the suggested optimal orientation of the imaging system. This can comprise, for example, the optimization of the one or more aspects of optimization, as described or otherwise envisioned herein.

[0070] According to an embodiment, the X-ray system allows the user to interact with the preview image such that they can provide further input as to how the system orientation should be adjusted so that they acquire images in the orientation that is optimal to them. They system may, optionally, save the user input and further fine-tune the trained neural network to user preference . Thus, according to an embodiment, the received approval to orient the one or more adjustable components to the predicted optimal orientation comprises a fine-tuning, from the user, of the predicted optimal orientation, and orienting comprises orienting the one or more adjustable components to a fine-tuned predicted optimal orientation.

[0071] In this embodiment, the user may additionally provide their preference as an input, which may be used to weight losses used, for example, during inference-time fine-tuning. For example, referring to FIG. 6 is an example slider that could allow users to indicate preference that controls the final orientation of the system and, therefore, the resulting image acquired. If the user wants the vasculature to be aligned with the direction of navigation rather than maximize the amount of relevant image features in the FOV, they may provide this preference as an input. Thus, the input may be provided using a slider, where if the slider is all the way to the right, a weight of 0 is applied to 1^ and a weight of 1 is applied to L2during finetuning or optimization. If the slider is all the way to the left, a weight of 1 is applied to Li and a weight of 0 is applied to L2during fine-tuning or optimization. The weight may change linearly as the slider moves between the two extremes.

[0072] At step 190 of method 100 depicted in FIG. 1, the X-ray system can obtain one or more subsequent X-ray images after the imaging system is optimally positioned. This results in improved X-ray imaging, as the one or more components are optimally oriented to optimize the one or more aspects of X- ray imaging. These aspects of X-ray imaging may be, for example, one or more of: (i) maximizing alignment of the X-ray imaging system with the subject’s anatomy, (ii) minimizing a region around the subject’s anatomy that is preferably excluded from the X-ray imaging, such that this region is minimized and the subject’s anatomy is maximized; (iii) maximizing alignment of the X-ray imaging system to collimate out anatomy to be excluded from X-ray imaging (such as maximizing collimation shutter alignment, among other alignments); and (iv) maximizing an amount of the subject’s anatomy to be included in the X-ray imaging, among other aspects.

[0073] According to another embodiment, an image obtained after the one or more adjustable components of the X-ray system have been oriented to the optimal orientation may be adjusted in postprocessing to further optimize the imagine. In this embodiment, an additional rotation parameter may be computed in order to be applied to the acquired image in post processing. For instance, if the user wants to maximize the amount of relevant image features in the FOV and also orient the image such that the vasculature is aligned with the direction of navigation, then the detector of the X-ray system may be oriented such that the amount of relevant image features in the FOV is maximized, and a rotation may be applied to the new image(s) in post-processing after image acquisition such that the vasculature in the images is aligned with the direction of navigation. Since rotation of an image may lead to areas without information in the rotated image, deep learning or other techniques may be used to fill in this missing information via extrapolation or inpainting (e.g., using GANs, diffusion models, etc.).

[0074] According to another embodiment, a 3D image may be available. For instance, if a 3DRA is acquired during treatment planning, optimizing the orientation of the C-arm to optimally visualize the treatment target may be combined with optimization of the L-arm to optimally collimate out anatomy around the treatment target that does not need to be imaged and / or with optimization of the detector to maximize the amount of relevant image features in the FOV, or to orient the image such that the vasculature is aligned with the direction of navigation, and so on.

[0075] Referring to FIG. 2 is a schematic representation of an X-ray orientation system 200. System 200 may be any of the systems described or otherwise envisioned herein, and may comprise any of the components described or otherwise envisioned herein. It will be understood that FIG. 2 constitutes, in some respects, an abstraction and that the actual organization of the components of the system 200 may be different and more complex than illustrated.

[0076] According to an embodiment, system 200 comprises a processor 220 capable of executing instructions stored in memory 230 or storage 260 or otherwise processing data to, for example, perform one or more steps of the method. Processor 220 may be formed of one or multiple modules. Processor 220 may take any suitable form, including but not limited to a central processing unit (CPU), graphical processing unit (GPU), tensor processing unit (TPU), neural processing unit (NPU), microprocessor, microcontroller, multiple microcontrollers, circuitry, field programmable gate array (FPGA), application-specific integrated circuit (ASIC), a single processor, or plural processors.

[0077] Memory 230 can take any suitable form, including a non-volatile memory and / or RAM. The memory 230 may include various memories such as, for example LI, L2, or L3 cache or system memory. As such, the memory 230 may include static random access memory (SRAM), dynamic RAM (DRAM),flash memory, read only memory (ROM), or other similar memory devices. The memory can store, among other things, an operating system. The RAM is used by the processor for the temporary storage of data. According to an embodiment, an operating system may contain code which, when executed by the processor, controls operation of one or more components of system 200. It will be apparent that, in embodiments where the processor implements one or more of the functions described herein in hardware, the software described as corresponding to such functionality in other embodiments may be omitted.

[0078] User interface 240 may include one or more devices for enabling communication with a user. The user interface can be any device or system that allows information to be conveyed and / or received, and may include a display, a mouse, and / or a keyboard for receiving user commands. In some embodiments, user interface 240 may include a command line interface or graphical user interface that may be presented to a remote terminal via communication interface 250. The user interface may be located with one or more other components of the system, or may be located remote from the system and in communication via a wired and / or wireless communications network.

[0079] Communication interface 250 may include one or more devices for enabling communication with other hardware devices. For example, communication interface 250 may include a network interface card (NIC) configured to communicate according to the Ethernet protocol. Additionally, communication interface 250 may implement a TCP / IP stack for communication according to the TCP / IP protocols. Various alternative or additional hardware or configurations for communication interface 250 will be apparent.

[0080] Storage 260 may include one or more machine-readable storage media such as read-only memory (ROM), random-access memory (RAM), magnetic disk storage media, optical storage media, hard disk drive (HDD), solid state drive (SSD), flash-memory devices, or similar storage media. In various embodiments, storage 260 may store instructions for execution by processor 220 or data upon which processor 220 may operate. For example, storage 260 may store an operating system 261 for controlling various operations of system 200.

[0081] It will be apparent that various information described as stored in storage 260 may be additionally or alternatively stored in memory 230. In this respect, memory 230 may also be considered to constitute a storage device and storage 260 may be considered a memory. Various other arrangements will be apparent. Further, memory 230 and storage 260 may both be considered to be non-transitory machine- readable media. As used herein, the term non-transitory will be understood to exclude transitory signals but to include all forms of storage, including both volatile and non-volatile memories.

[0082] While system 200 is shown as including one of each described component, the various components may be duplicated in various embodiments. For example, processor 220 may include multiple microprocessors that are configured to independently execute the methods described herein or are configured to perform steps or subroutines of the methods described herein such that the multiple processors cooperate to achieve the functionality described herein. Further, where one or more components of system 200 is implemented in a cloud computing system, the various hardware components may belong to separate physical systems. For example, processor 220 may include a first processor in a first server and a second processor in a second server. Many other variations and configurations are possible.

[0083] According to an embodiment, system 200 comprises or is in direct or indirect communication with an X-ray system or device 270. The X-ray system or device 270 can be any system or device configured to obtain X-ray imaging of a patient, such as a human being or an animal, among other targets. The X-ray system or device 270 may be a fixed system or a mobile system. According to an embodiment, the X-ray system or device 270 comprises one or more adjustable components, where the one or more adjustable components may be adjusted to achieve a goal of X-ray imaging as described or otherwise envisioned herein.

[0084] According to an embodiment, the X-ray orientation system 200 comprises or is in direct or indirect communication with an electronic medical record system and / or an electronic medical records (EMR) database 280 from which the information about patients, including demographic, diagnosis, and / or treatment information, may be obtained or received. For example, EMR database may comprise information about an imaging or treatment procedure for a patient, including the anatomy that will be imaged during the procedure. According to an embodiment, the electronic medical record system 280 may be a local or remote database and is in direct and / or indirect communication with system 200. Thus, according to an embodiment, the system comprises an electronic medical record database or system 280. Electronic medical records, as described here, also include information that may be described as electronic health records (EHR), patient health information (PHI), and so on.

[0085] According to an embodiment, storage 260 of system 200 may store one or more algorithms, modules, and / or instructions to carry out one or more functions or steps of the methods described or otherwise envisioned herein. For example, storage 260 may comprise, among other instructions or data, a trained X-ray orientation model 262, training instructions 263, application instructions 264, and / or reporting instructions 265.

[0086] According to an embodiment, the trained X-ray orientation model 262 of the X-ray orientation system 200 is trained to analyze extracted image features (as input to the model) to predict an optimalorientation of one or more adjustable components of the X-ray system (as output of the model). The trained X-ray orientation model can be any model that can be trained to utilize the input to generate the output, as described or otherwise envisioned herein. For example, the trained X-ray orientation model can be a neural network or other trained machine learning model. Thus, according to an embodiment, the X-ray orientation system comprises a trained X-ray orientation model that receives the input data and outputs an optimal orientation of the various one or more orientable parts of the X-ray imaging system such that an appropriate FOV of the region of interest (ROI) is imaged. The trained X-ray orientation model is unique based on the training data used to train the model. Once generated, the trained X-ray orientation model 262 can be utilized immediately, or it may be stored in local and / or remote memory for future use.

[0087] According to an embodiment, training instructions 263 direct the system to train an X-ray orientation model 262 of the X-ray orientation system 200. The instructions direct the system to retrieve, obtain, or receive training data. The training data can be any data sufficient to train the model to utilize the described input data to generate the described output. For example, the training data may comprise X-ray imaging for each of a plurality of patients and procedures, including images before and after optimization, including with ground truth optimization. The training instructions 263 further direct the system to train the X-ray orientation model using the obtained training data. The X-ray orientation model can be trained using a variety of different training methods. The training instructions 263 further direct the system to store the trained X-ray orientation model for future use.

[0088] Similarly, application instructions 264 direct the system to apply the trained X-ray orientation model 262 of the X-ray orientation system 200 to new data acquired at application or inference time. Application time or inference time refers to the application of the trained model. The instructions direct the system to retrieve, obtain, or receive data acquired at application or inference time, and predict an optimal orientation of one or more adjustable components of the X-ray system as described or otherwise envisioned herein.

[0089] According to an embodiment, the X-ray orientation system 200 is configured to process many thousands or millions of datapoints in the input data used to train the X-ray orientation model 262, such as via the training instructions 263. For example, generating a functional and skilled trained X-ray orientation model from a corpus of training data requires processing of millions of datapoints from input data and generated features. This can require millions or billions of calculations to generate a novel trained X-ray orientation model from those millions of datapoints and millions or billions of calculations. As a result, each trained X-ray orientation model is novel and distinct based on the input data and parameters of the model, and thus improves the functioning of the system. Generating a functional and skilled trained X-rayorientation model comprises a process with a volume of calculation and analysis that a human brain cannot accomplish in a lifetime, or multiple lifetimes.

[0090] According to an embodiment, reporting instructions 265 direct the system to provide the output of the system to a user, such as a clinician, via a user interface. The provided output can be any of the information as described or otherwise envisioned herein. The system may provide the information to a user via any mechanism, including but not limited to a visual display, an audible notification, a page, or any other method of notification. The information may be communicated by wired and / or wireless communication to another device. For example, the system may communicate the information to a monitor, screen, mobile phone, computer, laptop, wearable device, and / or any other device configured to allow display and / or other communication of the information.

[0091] All definitions, as defined and used herein, should be understood to control over dictionary definitions, definitions in documents incorporated by reference, and / or ordinary meanings of the defined terms.

[0092] The indefinite articles “a” and “an,” as used herein in the specification and in the claims, unless clearly indicated to the contrary, should be understood to mean “at least one.”

[0093] The phrase “and / or,” as used herein in the specification and in the claims, should be understood to mean “either or both” of the elements so conjoined, i.e., elements that are conjunctively present in some cases and disjunctively present in other cases. Multiple elements listed with “and / or” should be construed in the same fashion, i.e., “one or more” of the elements so conjoined. Other elements may optionally be present other than the elements specifically identified by the “and / or” clause, whether related or unrelated to those elements specifically identified.

[0094] As used herein in the specification and in the claims, “or” should be understood to have the same meaning as “and / or” as defined above. For example, when separating items in a list, “or” or “and / or” shall be interpreted as being inclusive, i.e., the inclusion of at least one, but also including more than one, of a number or list of elements, and, optionally, additional unlisted items. Only terms clearly indicated to the contrary, such as “only one of’ or “exactly one of,” or, when used in the claims, “consisting of,” will refer to the inclusion of exactly one element of a number or list of elements. In general, the term “or” as used herein shall only be interpreted as indicating exclusive alternatives (i.e. “one or the other but not both”) when preceded by terms of exclusivity, such as “either,” “one of,” “only one of,” or “exactly one of.”

[0095] As used herein in the specification and in the claims, the phrase “at least one,” in reference to a list of one or more elements, should be understood to mean at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of each and everyelement specifically listed within the list of elements and not excluding any combinations of elements in the list of elements. This definition also allows that elements may optionally be present other than the elements specifically identified within the list of elements to which the phrase “at least one” refers, whether related or unrelated to those elements specifically identified.

[0096] It should also be understood that, unless clearly indicated to the contrary, in any methods claimed herein that include more than one step or act, the order of the steps or acts of the method is not necessarily limited to the order in which the steps or acts of the method are recited.

[0097] In the claims, as well as in the specification above, all transitional phrases such as “comprising,” “including,” “carrying,” “having,” “containing,” “involving,” “holding,” “composed of,” and the like are to be understood to be open-ended, i.e., to mean including but not limited to. Only the transitional phrases “consisting of’ and “consisting essentially of’ shall be closed or semi-closed transitional phrases, respectively.

[0098] While several inventive embodiments have been described and illustrated herein, those of ordinary skill in the art will readily envision a variety of other means and / or structures for performing the function and / or obtaining the results and / or one or more of the advantages described herein, and each of such variations and / or modifications is deemed to be within the scope of the inventive embodiments described herein. More generally, those skilled in the art will readily appreciate that all parameters, dimensions, materials, and configurations described herein are meant to be exemplary and that the actual parameters, dimensions, materials, and / or configurations will depend upon the specific application or applications for which the inventive teachings is / are used. Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many equivalents to the specific inventive embodiments described herein. It is, therefore, to be understood that the foregoing embodiments are presented by way of example only and that, within the scope of the appended claims and equivalents thereto, inventive embodiments may be practiced otherwise than as specifically described and claimed. Inventive embodiments of the present disclosure are directed to each individual feature, system, article, material, kit, and / or method described herein. In addition, any combination of two or more such features, systems, articles, materials, kits, and / or methods, if such features, systems, articles, materials, kits, and / or methods are not mutually inconsistent, is included within the inventive scope of the present disclosure.

Claims

ClaimsWhat is claimed is:

1. A method (100) for predicting an orientation of an imaging device, the method comprising: obtaining (130) an initial image of an anatomy; extracting (140) at least one image feature of the anatomy from the initial image; and based on the extracted at least one image feature, predicting (150) an optimal orientation of one or more adjustable components of the imaging device for subsequent imaging of the anatomy.

2. The method of claim 1, wherein predicting the optimal orientation of the one or more adjustable components comprises applying a trained imaging orientation model configured to analyze the extracted at least one image feature.

3. The method of claim 1, further comprising obtaining (120) information comprising an identification of the anatomy to be imaged by the imaging device, and wherein predicting the optimal orientation of the one or more adjustable components comprises analyzing the obtained information to predict the optimal orientation of the one or more components.

4. The method of claim 1, further comprising: obtaining (170), from a user via a user interface, approval to orient the one or more adjustable components to the predicted optimal orientation; and orienting (180), by the imaging device, the one or more adjustable components to the predicted optimal orientation.

5. The method of claim 4, wherein: the approval comprises a fine-tuning, from the user, of the predicted optimal orientation, and orienting the one or more adjustable components comprising adjusting the one or more adjustable components to the fine-tuned predicted optimal orientation.

6. The method of claim 1, wherein the predicting of the optimal orientation of the one or more adjustable components comprises at least one of: (i) maximizing alignment of the imaging device with the anatomy; (ii) minimizing a region around the anatomy to be excluded from the X-ray imaging; (iii) maximizing alignment of the imaging device to collimate out a portion of the anatomy to be excluded fromthe subsequent imaging; and (iv) maximizing an amount of the anatomy to be included in the subsequent imaging.

7. The method of claim 1, further comprising: providing (160), via a user interface, the predicted optimal orientation of the one or more adjustable components of the X-ray system to a user as instructions to orient the one or more adjustable components to the optimal orientation or to request approval for the imaging device to orient the one or more adjustable components to the predicted optimal orientation, or automatically orienting (160), by the imaging device , the one or more adjustable components to the predicted optimal orientation.

8. The method of claim 7, wherein providing, via a user interface, the predicted optimal orientation comprises providing a predicted image of the anatomy if the one or more adjustable components are adjusted to the predicted optimal orientation.

9. The method of claim 7, wherein providing, via a user interface, the predicted optimal orientation comprises providing a visual display of the optimal orientation of one or more adjustable components.

10. An system (200) for predicting an optimal orientation of an imaging system, the system comprising : a processor in communication with memory, the processor configured to: obtain an initial image of an anatomy; extract at least one image feature of the anatomy from the initial image; and based on the extracted at least one image feature, predict an optimal orientation of one or more adjustable components of the imaging device for subsequent imaging of the anatomy.

11. The system of claim 10, wherein the processor is configured to apply a trained imaging orientation model to predict the optimal orientation of the one or more adjustable components based on the extracted at least one image feature.

12. The system of claim 10, wherein the processor is further configured to automatically orient the one or more adjustable components to the predicted optimal orientation.

13. The system of claim 10, wherein, to predict the optimal orientation, the processor is configured to at least one of: (i) maximize alignment of the imaging device with the anatomy; (ii) minimize a regionaround the anatomy to be excluded from the subsequent imaging; (iii) maximize alignment of the X-ray system to collimate out a portion of the anatomy to be excluded from the subsequent imaging; and (iv) maximize an amount of the anatomy to be included in the subsequent imaging.

14. The system of claim 10, further comprising a user interface configured to provide, to a user, the predicted optimal orientation of the one or more adjustable components of the X-ray system.

15. The system of claim 14, wherein the processor is configured to provide the optimal orientation as at least one of: (i) a predicted image of the anatomy if the one or more adjustable components of the imaging system were adjusted to the predicted optimal orientation; and (ii) a visual display of the optimal orientation of one or more adjustable components.

16. The system of claim 10, further comprising: the imaging device comprising the one or more adjustable components and configured to obtain the initial image of the anatomy and perform the subsequent imaging of the anatomy.

17. A non-transitory computer-readable storage medium having stored a computer program comprising instructions which, when executed by a processor, cause the processor to: obtain an initial image of an anatomy; extract at least one image feature of the anatomy from the initial image; and based on the extracted at least one image feature, predict an optimal orientation of one or more adjustable components of the imaging device for subsequent imaging of the anatomy.

Images