Method for modifying medical imaging protocol parameters

Abstract

The present disclosure relates to a computer-implemented method for modifying medical imaging protocol parameters, comprising: receiving modified protocol parameters for an imaging protocol; and determining whether the modified protocol parameter is acceptable based on at least one of the acquired image acceptability check and the parameter acceptability check. In addition, the present disclosure also relates to a computer readable medium comprising computer executable instructions, a system for medical imaging, and a radiotherapy device.

Description

Technical Field

[0001] The present disclosure relates to medical imaging protocols, and in particular, to methods and systems for modifying medical imaging protocol parameters. Background Art

[0002] Radiation therapy can be described as the use of ionizing radiation (such as X-rays) to treat the human or animal body. Radiation therapy is often used to treat tumors in a patient or subject. In such treatment, ionizing radiation is used to irradiate and thereby destroy or damage cells that form part of the tumor.

[0003] Radiotherapy equipment generally includes a gantry for supporting a beam generation system or other radiation source that can rotate around the patient. For example, for a linear accelerator (linac) device, the beam generation system may include a radio frequency energy source, an electron source, an accelerating waveguide, a beam shaping device, and the like.

[0004] The radiotherapy equipment may also include a medical imaging device, such as a magnetic resonance (MR) imaging device, which is configured to obtain images of the subject. Images may be taken immediately before treatment delivery in order to adjust or recalculate the treatment plan, such as to take into account inter-fractional changes in the patient's anatomical structure. A limitation of this approach is that the artifacts exhibited by the acquired images will affect the quality of the image analysis and, therefore, the quality of the adapted treatment plan. For example, image artifacts will affect the quality of image registration between pre-treatment computed tomography (CT) and daytime pre-beam MR images. Alternatively, in an automated imaging workflow, image artifacts will adversely affect the quality of image analysis using deep learning techniques. For example, image artifacts will adversely affect the quality of contours or synthetic CT calculated from daytime MR images using deep learning techniques. MR or other medical imaging may also be used for motion management purposes to support gating or tracking delivery of radiotherapy.

[0005] There are many sources of MR imaging artifacts that may affect the MR images and therefore the radiation therapy workflow. For example, metal implants in the patient may cause artifacts such as signal loss and / or geometric distortion due to magnetic field inhomogeneities associated with local magnetic susceptibility. Patient motion (e.g., respiratory motion, cardiac cycle, peristalsis, body motion, etc.) may cause ghosting artifacts. For Cartesian sequences, ghosting artifacts appear along the phase encoding direction. Other artifacts include, but are not limited to, Gibbs rings, chemical shifts, B1 inhomogeneities, radial streaks, and other artifacts known to those skilled in the art.

[0006] Image artifacts can be minimized by optimizing the protocol parameters of the imaging protocol. Image artifacts can also be reduced by carefully selecting sequences. For example, geometric distortion can be reduced by applying three-dimensional (3D) distortion correction and / or by increasing the receiver bandwidth. However, the presence and severity of artifacts depend on the patient, so protocol parameter optimization may also vary between patients. Known imaging devices will only allow the use of specific validated protocols, which are locked and do not allow any protocol parameters to be changed, customized or optimized for different patients and / or clinical workflows.

[0007] There is a need to allow users to use, modify, customize and / or optimize imaging protocols (optionally as part of a clinical workflow).

[0008] The present disclosure seeks to address these and other shortcomings encountered in the prior art. Summary of the invention

[0009] The present disclosure relates to a computer-implemented method for modifying medical imaging protocol parameters, comprising: receiving modified protocol parameters for an imaging protocol; and determining whether the modified protocol parameters are acceptable based on at least one of an acquired image acceptability check and a parameter acceptability check.

[0010] Preferably, the method further comprises updating protocol parameters based on said modified protocol parameters.

[0011] Preferably, the method further comprises outputting and / or storing a determination whether said modified protocol parameters are acceptable.

[0012] Preferably, the acquired image acceptability check includes: acquiring an image of the subject using a protocol having the modified protocol parameters; determining a similarity metric between the acquired image and a verified image; and determining whether the modified protocol parameters are acceptable based at least in part on the similarity metric.

[0013] Preferably, said similarity measure is associated with a geometric transformation between said acquired image and said verified image.

[0014] Preferably, the geometric transformation comprises a deformation vector field.

[0015] Preferably, determining the geometric transformation comprises determining at least one of the x, y and / or z displacement components of the deformation vector field and / or a scalar length of at least one of the displacement components. Determining whether the modified protocol parameters are acceptable is based at least in part on at least one of the x, y and / or z displacement components of the deformation vector field and / or a scalar length of at least one of the displacement components.

[0016] Preferably, the modified protocol parameters are determined to be acceptable if the scalar length of the threshold ratio of the x, y and / or z displacement components is less than or equal to the maximum scalar length. The threshold ratio is in the range of 60% to 100%, preferably the threshold ratio is in the range of 80% to 100%, more preferably the threshold ratio is in the range of 90% to 100%, even more preferably the threshold ratio is about 95%. The maximum scalar length is in the range of 0.5 mm to 4 mm, preferably the maximum scalar length is in the range of 1.5 mm to 2.5 mm, more preferably the maximum scalar length is about 2 mm.

[0017] Preferably, the maximum scalar length is based on the resolution of the verified image.

[0018] Preferably, determining the geometric transformation between the acquired image and the verified image comprises attempting to register the acquired image with the verified image. If the attempt to register the acquired image with the verified image is unsuccessful and / or the geometric transformation cannot be determined, determining that the modified protocol parameters are unacceptable.

[0019] Preferably, the validated images are acquired using an imaging protocol having unmodified or validated protocol parameters.

[0020] Preferably, said similarity measure value is associated with a structural similarity index measure or a normalized cross-correlation measure between said acquired image and said verified image.

[0021] Preferably, the parameter acceptability check includes identifying whether the modified protocol parameter is a key parameter or a performance parameter, and checking the identified modified protocol parameter against a predetermined value. Identifying whether the modified protocol parameter is a key parameter includes identifying whether the modified protocol parameter corresponds to at least one of bandwidth, 3D geometric distortion, field of view, sound pressure level, and / or specific absorption rate. Identifying whether the modified protocol parameter is a performance parameter includes identifying whether the modified protocol parameter corresponds to at least one of signal-to-noise ratio, contrast, body view, acquisition time, acquisition resolution, and / or fat suppression.

[0022] Preferably, the method further comprises outputting and / or storing a determination whether the modified protocol parameters are acceptable, and optionally storing the modified protocol parameters and their determination.

[0023] Preferably, said modified protocol parameters are received from a user input device.

[0024] Preferably, the method further comprises: performing artifact detection on the acquired image. Performing the artifact detection comprises detecting, locating and / or segmenting artifacts in at least one of the acquired image and the verified image.

[0025] Preferably, performing said artifact detection comprises reporting image quality of at least one of said acquired image and said verified image.

[0026] Preferably, the computer vision tool outputs alternative modified protocol parameters based at least in part on reported image quality of the acquired image and / or the verified image.

[0027] The present disclosure also relates to a method for medical image acquisition, comprising: the aforementioned method for medical imaging protocol parameters; wherein, if it is determined that the modified protocol parameters are acceptable, a protocol having the acceptable modified protocol parameters is used to acquire subsequent images.

[0028] Preferably, the medical imaging is magnetic resonance imaging.

[0029] The present disclosure also relates to a computer-readable medium comprising computer-executable instructions, which, when executed by a processor, cause the processor to perform the above-mentioned method.

[0030] The present disclosure also relates to a system for medical imaging, comprising: a medical imaging device; a processor; and a computer-readable medium comprising computer-executable instructions, wherein when the computer-executable instructions are executed by the processor, the processor executes the above-mentioned method.

[0031] The present disclosure also relates to a radiotherapy device, comprising the above-mentioned system for medical imaging. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Specific examples will now be described, by way of example only, with reference to the accompanying drawings, in which:

[0033] Figure 1 A radiation therapy device or apparatus according to the present disclosure is depicted;

[0034] Figure 2 A method for modifying medical imaging protocol parameters according to the present disclosure is depicted;

[0035] Figure 3 depicts an acquired image acceptability check in accordance with the present disclosure;

[0036] Figure 4 depicts a parameter acceptability check in accordance with the present disclosure;

[0037] Figure 5 A radiation therapy apparatus including a computing system according to the present disclosure is depicted;

[0038] Figure 6 A computer program product according to the present disclosure is depicted. DETAILED DESCRIPTION

[0039] Overview

[0040] A method for modifying medical imaging protocol parameters is provided, comprising: receiving modified protocol parameters for an imaging protocol; and determining whether the modified protocol parameters are acceptable based on at least one of an acquired image acceptability check and a parameter acceptability check. This means that the modified protocol parameters can be evaluated based on the impact of the modified protocol parameters on the acquired images and / or based on the parameters themselves. This provides customizability without affecting image quality or imaging protocol functionality, and ensures patient safety and comfort within conservative boundaries.

[0041] Detailed description

[0042] Figure 1 A radiation therapy apparatus adapted and configured to deliver radiation beams to a patient during radiation therapy is depicted.In order to provide useful accompanying information to the present disclosure, a general description of the apparatus and its constituent components will be provided. Figure 1 The device depicted in is in accordance with the present disclosure and is suitable for use with the disclosed systems and devices. Figure 1 The device in the embodiment is a MR (magnetic resonance) linear accelerator, but the embodiments of the present disclosure can also be any radiation therapy device, such as a linear accelerator device.

[0043] Figure 1 The depicted device 100 is an MR linear accelerator. The device 100 includes an MR imaging device 112 and a radiation therapy (RT) device that may include a linear accelerator device. The MR imaging device 112 is shown in cross section in the schematic diagram. In operation, the MR scanner produces an MR image of the patient, and the linear accelerator device produces and shapes the radiation beam according to the radiation therapy plan and directs it toward a target area in the patient's body. The depicted device does not have a typical "housing" that would cover the MR imaging device 112 and the RT device in a commercial environment such as a hospital.

[0044] Figure 1The depicted MR linear accelerator apparatus includes a radio frequency wave source 102, a waveguide 104, an electron source 106, a radiation source 106, a collimator 108 (e.g., a multi-leaf collimator configured to collimate and shape the beam), an MR imaging device 112, and a patient support surface 114. In use, the apparatus also includes a housing (not shown) that defines a bore together with the annular gantry. When an MR scan and / or radiation therapy is initiated, the movable support surface 114 can be used to move a patient or other subject into the bore. The MR imaging device 112, the RT device, and the subject support surface actuator are communicatively coupled to a controller or processor. The controller is also communicatively coupled to a memory device that includes computer executable instructions that can be executed by the controller.

[0045] The RT device includes a radiation source and a radiation detector (not shown). Typically, the radiation detector is positioned diametrically opposite to the radiation source. The radiation detector is adapted and configured to generate radiation intensity data. In particular, the radiation detector is positioned and configured to detect the intensity of radiation that has passed through the subject. The radiation detector may also be described as a radiation detection device and may form part of a portal imaging system.

[0046] The radiation source may include a beam generating system. For a linear accelerator, the beam generating system may include a radio frequency energy source 102, an electron gun 106, and a waveguide 104. The radiation source is attached to a rotatable gantry 116 to rotate with the gantry 116. In this way, the radiation source can rotate around the patient so that the treatment beam 110 can be applied from different angles around the gantry 116. In a preferred embodiment, the gantry is continuously rotatable. In other words, the gantry can rotate 360 ​​degrees around the patient, and can actually continue to rotate more than 360 degrees. The gantry can be annular. In other words, the gantry can be an annular gantry.

[0047] The RF wave source 102 (e.g., a magnetron) is configured to generate RF waves. The RF (RF) wave source 102 is coupled to the waveguide 104 via a circulator 118 and is configured to input RF wave pulses into the waveguide 104. The RF waves can pass from the RF wave source 102 through the RF input window and enter the RF input connecting pipe or tube. The electron source 106 (e.g., an electron gun) is also coupled to the waveguide 104 and is configured to inject electrons into the waveguide 104. In the electron gun 106, electrons are thermally emitted from the cathode filament as the filament is heated. The temperature of the filament controls the number of electrons injected. The injection of electrons into the waveguide 104 is synchronized with the RF wave pumping into the waveguide 104. The RF wave source 102, the electron source, and the waveguide 104 are designed and operated so that the RF waves accelerate the electrons to very high energies as the electrons propagate through the waveguide 104.

[0048] The design of the waveguide 104 depends on whether the linear accelerator uses standing waves or traveling waves to accelerate electrons, although the waveguide generally includes a series of cells or cavities, each connected by a hole or "aperture" through which the electron beam can pass. The cavities are coupled so as to produce a suitable electric field pattern that accelerates the electrons propagating through the waveguide 104. As the electrons are accelerated in the waveguide 104, the electron beam path is controlled by an appropriate arrangement of steering magnets or steering coils surrounding the waveguide 104. The arrangement of steering magnets may include, for example, two sets of quadrupole magnets.

[0049] Once the electrons are accelerated, they enter a flight tube. The flight tube may be connected to the waveguide by a connecting tube. Such a connecting tube or connecting structure may be referred to as a drift tube. The electrons travel toward a heavy metal target, which may include, for example, tungsten. As the electrons travel through the flight tube, an arrangement of focusing magnets is used to direct and focus the beam on the target.

[0050] To ensure that the propagation of electrons is not hindered as the electron beam travels toward the target, the waveguide 104 is evacuated using a vacuum system including a vacuum pump or a vacuum pump arrangement. The pump system is capable of creating (UHV) conditions in the waveguide 104 and the flight tube. The vacuum system also ensures ultra-high vacuum conditions in the electron gun. Electrons can be accelerated to speeds close to the speed of light in the vacuum waveguide 104.

[0051] The radiation source is configured to direct a therapeutic radiation beam 110 toward a patient positioned on a patient support surface 114. The radiation source may include a heavy metal target toward which high energy electrons exiting a waveguide are directed. When the electrons hit the target, X-rays are generated in various directions. A primary collimator may block X-rays traveling in a particular direction and only pass forward traveling X-rays to produce the therapeutic beam 110. The X-rays may be filtered and may pass through one or more ion chambers for dose measurement. The beam may be shaped in various ways by a beam shaping device, such as by using a multi-leaf collimator 108, before entering the patient as part of the radiation therapy.

[0052] In some embodiments, the radiation source is configured to emit an X-ray beam or an electron particle beam. Such embodiments allow the device to provide electron beam therapy, a type of external beam therapy in which electrons rather than X-rays are directed toward the target area. By adjusting the components of the linear accelerator, it is possible to "switch" between a first mode that emits X-rays and a second mode that emits electrons. In essence, it is possible to swap between the first mode and the second mode by moving a heavy metal target in or out of the electron beam path and replacing it with a so-called "electron window." The electron window is substantially transparent to electrons and allows the electrons to leave the flight tube.

[0053] The subject or patient support surface 114 is configured to move between a first position roughly outside the hole and a second position roughly inside the hole. In the first position, the patient or subject can be placed on the patient support surface. Then, the support surface 114 and the patient can be moved to the second position in the hole so that the patient is imaged by the MR imaging device 112 and / or imaged or treated using an RT device. The movement of the patient support surface is implemented and controlled by a subject support surface actuator, which can be described as an actuating mechanism. The actuating mechanism is configured to move the subject support surface in a direction parallel to the central axis of the hole and defined by the central axis of the hole. The terms "subject" and "patient" are used interchangeably herein, so that the subject support surface can also be described as a patient support surface. The subject support surface can also be referred to as a movable or adjustable sofa or table.

[0054] Figure 1 The radiation therapy apparatus / device shown also includes a magnetic resonance imaging device 112. The MR imaging device 112 is configured to obtain or acquire an image of a subject positioned (i.e., located) on a subject support surface 114. The MR imaging device 112 may also be referred to as an MR imager. The MR imaging device 112 may be a conventional MR imaging device that operates in a known manner to obtain or acquire MR data (e.g., MR images). Those skilled in the art will appreciate that such an MR imaging device 112 may include a main magnet, one or more gradient coils, one or more receiving coils, and a radio frequency pulse applicator. The operation of the MR imaging device is controlled by a controller.

[0055] The controller is a computer, processor, or other processing device. The controller may be formed of multiple discrete processors; for example, the controller may include an MR imaging device processor that controls the MR imaging device 112; an RT device processor that controls the operation of the RT device; and a subject support surface processor that controls the operation and actuation of the subject support surface. The controller is communicatively coupled to a memory, such as a computer readable medium.

[0056] The linear accelerator device also includes several other components and systems that will be understood by those skilled in the art. For example, in order to ensure that the linear accelerator does not leak radiation, appropriate shielding is also provided.

[0057] The disclosed method allows modification of imaging protocol parameters, enabling customization of imaging protocols while ensuring maintained image quality and optimal performance. The imaging protocol of the method disclosed herein may involve MR imaging, or may be an MR imaging protocol, and MR imaging will be used as a specific example to illustrate the present disclosure. However, the disclosed method may also additionally or alternatively involve other types of medical imaging and medical imaging protocols, such as CT imaging, cone beam CT imaging, single photon emission computed tomography (SPECT) imaging, and / or positron emission tomography (PET) imaging.

[0058] Figure 2 A method 200 for modifying imaging protocol parameters according to one aspect of the present disclosure is depicted. The method 200 includes receiving 202 modified protocol parameters for an imaging protocol; and determining 204 whether the modified protocol parameters are acceptable. The determination 204 whether the modified protocol parameters are acceptable is based on at least one of an acquired image acceptability check 300 and a parameter acceptability check 400. In other words, the present disclosure provides one aspect of the method 200 for modifying imaging protocol parameters related to assessing the acceptability of acquired images, and one aspect of the method 200 for modifying medical imaging protocol parameters related to assessing parameter acceptability. Figure 3 The image acceptability check acquired according to the present disclosure is depicted in Figure 2 and Figure 3 Together, one aspect of a method 200 related to evaluating parameter acceptability is depicted. Similarly, Figure 4 Depicts a parameter acceptability check according to the present disclosure such that Figure 2 and Figure 4 Together, one aspect of a method 200 related to evaluating parameter acceptability is depicted. In some examples of the method 200, an acquired image acceptability check and a parameter acceptability check may be performed.

[0059] In some examples, method 200 also includes performing artifact detection on the acquired images. The method may also include outputting and / or storing 220 a determination of whether the modified protocol parameters are acceptable based on one or both of the acquired image acceptability check and the parameter acceptability check. Method 200 is a computer-implemented method and may be used with a radiation therapy device and / or an imaging device (e.g., Figure 1 Equipment 100, Figure 5 System 500, Figure 1 The imaging device 112 and / or Figure 5 The image acquisition device 540) is used in combination with, and optionally executed by, it.

[0060] The method 200 includes receiving 202 modified protocol parameters for an imaging protocol. Receiving 202 modified protocol parameters for an imaging protocol may include, for example, obtaining, inputting, or accessing modified protocol parameters for an imaging protocol by or at an imaging device. In some examples, the modified protocol parameters are input by a user. The method 200 may also include prompting a user to input the modified protocol parameters. The parameters may be input at an input device such as a user input device. The input device may include a user interface, optionally including a graphical user interface (GUI), and may be located or included in the radiotherapy device 100 and / or the imaging device 112 and / or a computing device that is communicatively coupled to the radiotherapy device and / or the imaging device. In some examples, the user inputs the modified protocol parameters by any means disclosed herein, and the modified protocol parameters are sent and / or received, for example, from the input device and / or received by the imaging device 112, for use in the method. Receiving the modified protocol parameters from the user input device allows intuitive interaction between the user and the method and system, thereby providing an easy-to-operate device for customizing medical imaging protocols. The modified protocol parameters may also be received from a database, and / or based at least in part on the treatment plan for the subject.As used herein, the term "subject" may refer to a patient or a specific portion or sub-portion of a patient.

[0061] The method includes receiving 202 modified protocol parameters for an imaging protocol to allow for customization of the imaging protocol, enabling modification of the protocol parameters to adjust the protocol for a given patient and / or workflow. This allows for reduction or prevention of artifacts, improved image quality, and improved quality of treatment plans adapted or recalculated using the images. Additionally, the method facilitates modification of protocol parameters through an authorized or permitted process. This reduces the risk of a user attempting to edit or modify a protocol through unauthorized or unsupervised means or ad hoc workarounds.

[0062] The method 200 includes determining 204 whether the modified protocol parameters are acceptable. The determination is based on at least one of an acquired image acceptability check 300 and a parameter acceptability check 400. In some examples, the method 200 also includes performing at least one of an acquired image acceptability check and a parameter acceptability check. Figure 3 and Figure 4 Examples of acquired image acceptability checks 300 and parameter acceptability checks 400 are described in more detail.

[0063] Figure 3An acquired image acceptability check is depicted according to one aspect of a method 200 for modifying medical imaging protocol parameters. In this aspect, the method 200 includes: receiving 202 modified protocol parameters for an imaging protocol; and determining 204 whether the modified protocol parameters are acceptable based at least on the acquired image acceptability check 300. The acquired image acceptability check 300 includes acquiring 302 an image of a subject using the protocol with the modified protocol parameters; determining 304 a similarity metric between the acquired image and a validated image using image registration; and determining 306 whether the modified protocol parameters are acceptable based at least in part on the similarity metric.

[0064] Acquiring 302 an image of a subject using a protocol with modified parameters includes acquiring image data. In an example where the imaging protocol involves MR imaging, the acquisition of the image and / or the acquisition of the image data is performed by the MR imaging device 112. The imaging protocol may include a plurality of protocol parameters. At least one of the plurality of protocol parameters of the imaging protocol may be modified. The received modified protocol parameters correspond to some or all of the plurality of protocol parameters of a given imaging protocol. In other words, the imaging protocol with the modified protocol parameters may also include one or more other protocol parameters that are not modified. In some examples, the unmodified protocol parameters may include at least one of the MR sequence type parameters and / or which RF coils will be used for imaging. In some examples, the MR sequence type may be selected, and then at least one parameter (such as a field of view parameter) may be subsequently modified, while other parameters remain unchanged (such as a TR / TE parameter). Such modifications may be different for different patients, for example, for one patient, the TR / TE parameters may be modified and the field of view parameters remain unchanged, while for another patient, the TR / TE parameters may remain unchanged and the field of view parameters are modified. As another example, the imaging protocol may include a fat suppression parameter value that has been modified from a previous fat suppression parameter value, and the imaging protocol may also include a specific absorption rate (SAR) parameter that has not been modified from a SAR parameter to be used with the previous fat suppression parameter value. Other examples of parameters that may remain unmodified include at least one of the type of RF pulse used, the maximum strength of the gradient / slope, and / or the coil used.

[0065] In some examples, an image is acquired using an imaging protocol with unmodified or verified protocol parameters. Unmodified protocol parameters may be received as part of method 200. Unmodified protocol parameters employ "default" or "standard" or preset values ​​and / or may be automatically determined based at least in part on modified parameters. Default or standard or preset protocol parameters are set as part of a given imaging protocol and may vary between given imaging protocols. An imaging protocol corresponds to a verified image such that a verified image is acquired using an imaging protocol without modified protocol parameters, and the acquired image of the method is acquired using modified protocol parameters. In this manner, a user may start with an imaging protocol and a corresponding verified image, modify the protocol by providing modified protocol parameters, and then acquire an image using an imaging protocol with modified parameters. The acquired image is then used in a registration step. The registration step includes registering the acquired image or attempting to register the acquired image to the verified image, and conventional image registration techniques known to those skilled in the art may be used. The registration step may be used to determine whether the modified protocol parameters are acceptable based on how or whether the acquired image differs from the verified image. The registration step may include an alignment step using mutual information from the acquired image and the verified image. The registration step may include using a viewer to switch between the two images to assess how similar the images are and whether they are correctly registered.

[0066] Various alternative image registration techniques are possible, which may each include the following exemplary steps:

[0067] 1) Determine the fixed / target image and the moving / source image. Register the moving image to the fixed image.

[0068] 2) Determine the registration type, parameters and domain. There are different types of registration (linear, rigid, non-rigid, etc.) parameters. Usually, the domain where the registration is performed is the image domain.

[0069] 3) Make sure the resolution of both acquisitions is the same so that the pixels / voxels are comparable.

[0070] 4) Registration is performed by looking at corresponding features in the two images, or by calculating a correlation measure between the images (e.g. corresponding lines, contours, etc.) to see the intensity of similarity. An attempt is then made to maximize the correspondence by changing the mobile / source image. Mathematically, this is done by minimizing a cost function. The higher the correlation between the two images, the lower the cost function, so when the cost function is minimized, the images are considered to be registered.

[0071] Further steps can be taken to improve the image registration, for example, by performing the registration at different resolution levels (first a coarse resolution, then a fine resolution), or by using prior information about the underlying anatomy (e.g., brains will not deform, but they will rotate).

[0072] The present method comprising acquiring 302 an image of a subject using a protocol with modified parameters facilitates comparison between an acquired image acquired using the modified protocol parameters and a validated image. This allows the acquired modified protocol parameters and images to be tested, compared or evaluated based on validated images and / or validated protocols. Thus, protocol parameters may be modified without compromising imaging functionality, quality or performance. In examples where the imaging protocol relates to MR imaging or is an MR imaging protocol, the acquired and validated images may each be MR images.

[0073] In one method, a similarity metric is associated with a geometric transformation between the acquired image and the verified image. Using image registration to determine 304 a similarity metric between the acquired image and the verified image includes determining a geometric transformation between the acquired image and the verified image. The geometric transformation between the acquired image and the verified image can be determined, for example, using a method based on comparing individual pixel values ​​of the two images. As explained with reference to step 302, the verified image can be an image acquired using an imaging protocol with unmodified protocol parameters (i.e., using a "standard" or "preset" or "verified" imaging protocol). The geometric transformation is used as a measure of similarity or geometric fidelity between the acquired image and the verified image. For example, a minimum transformation indicates that the acquired image is geometrically similar to the verified image, and similarly, the modified parameters do not result in any unacceptable changes to the image acquisition or the acquired image. Determining 306 whether the modified protocol parameters are acceptable is based at least in part on the geometric transformation. Although the modified parameters can reduce or prevent image artifacts, the overall structure or features of the image can remain substantially the same or similar. In other words, image artifacts need to be reduced or prevented, however, minimal deviations from the validation image will be acceptable relative to other aspects. Thus, using the disclosed method for modifying imaging protocol parameters, image quality can be improved relative to artifact reduction, and other degradation of image quality or other deleterious effects on image acquisition or the acquired images can be monitored and / or avoided.

[0074] In some examples, the geometric transformation includes a deformation vector field. The deformation vector field may include x, y, and / or z displacement components. That is, the deformation vector field may include at least one x displacement component, at least one y displacement component, and / or at least one z displacement component. The deformation vector field may include multiple x displacement components, multiple y components, and / or multiple z components. One or more displacement components include a scalar length. Determining the geometric transformation includes determining at least one of the deformation vector fields, at least one of the x, y, and / or z displacement components of the deformation vector field, and / or a scalar length of at least one of the displacement components. Determining 306 whether the modified protocol parameters are acceptable is based at least in part on at least one of the x, y, and / or z displacement components of the deformation vector field and / or the scalar length of at least one displacement component.

[0075] The registration step may include attempting to register the acquired image and / or successfully registering the acquired image to the verified image. If the attempt to register the acquired image with the verified image is unsuccessful, that is, if the acquired image cannot be registered with the verified image, or the geometric transformation between the acquired image and the verified image cannot be determined, then the modified protocol parameters may be determined to be unacceptable. This ensures that the modified protocol parameters that result in an adverse change in image quality may be identified. The modified protocol parameters and / or their unacceptable determinations may be output and / or stored 220 to improve the efficiency of the method in the event that the same modified protocol parameters are received in the future, and to allow for the inspection of unacceptable modified protocol parameters independent of the performance of the method 200. In some examples, if the modified protocol parameters are determined to be acceptable, the protocol parameters are updated based on the modified protocol parameters. The protocol parameters to be updated may be, for example, stored protocol parameters, verified protocol parameters, and / or original protocol parameters.

[0076] In some aspects of the present disclosure relating to evaluating the acceptability of an acquired image, a similarity metric value is associated with a structural similarity index metric or a normalized cross-correlation metric between the acquired image and the verified image. Techniques for determining a structural similarity index metric or a normalized cross-correlation metric are known to those skilled in the art. A structural similarity index metric method may identify at least one structure (such as a circle) in one of the images and attempt to identify that structure or a similar structure in the other image. A structural similarity index method may involve analysis of brightness, contrast, and structure within the image and calculation of a single value for each pixel. A structural similarity index metric gives a relative comparison and error value, rather than an absolute error value. A normalized cross-correlation method may include comparing pixel values ​​and determining whether the pixel is at a minimum, such as by calculating the distance as similar pixel values. A normalized cross-correlation method may include normalizing the data before calculating the difference between pixels in the two images. A normalized cross-correlation metric provides a relative comparison between the two images.

[0077] The method includes determining 304 a similarity measure between the acquired image and the verified image using image registration to facilitate an efficient comparison between the verified image and an image acquired using an imaging protocol with modified protocol parameters. This means that the modified protocol parameters can be evaluated to assess any changes to the acquired image compared to the verified image.

[0078] Aspects of method 200 involving evaluating the acceptability of an acquired image include determining 306 whether the modified protocol parameters are acceptable based at least in part on a similarity metric value. In general, determining whether the modified protocol parameters are acceptable based at least in part on a similarity metric can include determining whether the similarity metric is an acceptable metric. In some examples, this includes determining whether a deformation vector field of a geometric transformation includes a displacement component on an acceptable scale. In other words, if the geometric transformation or other similarity metric between the acquired image and the verified image corresponds to a sufficiently small or acceptable difference between the acquired image and the verified image, the modified protocol parameters can be determined to be acceptable.

[0079] In some examples, whether the modified protocol parameters are acceptable is determined based at least in part on a deformation vector field of the geometric transformation, at least one of the x, y, and / or z displacement components of the deformation vector field, and / or a scalar length of at least one displacement component.

[0080] In one aspect of the method 200 related to evaluating the acceptability of an acquired image, if the acquired image is within a specific transformation of a verified image, the modified protocol parameters are determined to be acceptable. In particular, if a specific ratio of the x, y and / or z components of the deformation vector field has a scalar length that is less than or equal to or strictly less than the maximum scalar length, the modified protocol parameters are determined to be acceptable. The certain ratio may be referred to as a threshold ratio, an optimal ratio, a minimum ratio, or a reference ratio. The maximum scalar length may be referred to as a threshold scalar length or a reference scalar length. Therefore, if the scalar length of the threshold ratio of the x, y and / or z displacement components is less than or equal to the maximum scalar length, the modified protocol parameters are determined to be acceptable. In some examples, the maximum scalar length is a value in the range of not less than 0.5 mm to not more than 4 mm. In other examples, the maximum scalar length is a value in the range of not less than 1.5 mm to not more than 2.5 mm, and most preferably may be 2 mm. The threshold ratio may be a value within the range of not less than 60% to not more than 100%, or a value within the range of not less than 80% to not more than 100%, or a value within the range of not less than 90% to not more than 100%, and most preferably may be 95%.

[0081] In some examples, determining 306 that the modified protocol parameters are acceptable includes determining that at least one of the x, y, and / or z displacement components and / or the scalar length of at least one of the displacement components is less than or equal to or strictly less than a distance corresponding to the resolution of the acquired and / or verified image. In other words, determining 306 includes determining whether the deformation vector field of the geometric transformation includes a displacement component on a scale corresponding to the image resolution of the acquired and / or verified image, and / or the maximum scalar length corresponds to the image resolution, or corresponds to a scale or distance of the image resolution. Thus, the maximum scalar length can be based on the resolution of the verified image. If the displacement component and / or the scalar length of the displacement component is less than or equal to or strictly less than a distance or scale corresponding to the image resolution, then the modified protocol parameters are determined to be acceptable. If the displacement component and / or the scalar length of the displacement component is greater than (or, in some examples, equal to) a distance or scale corresponding to the image resolution, then the modified protocol parameters are determined to be unacceptable.

[0082] In some examples, the distance or scale corresponding to the resolution of the image is approximately 1 mm. Thus, in some examples, the modified protocol parameters are determined to be acceptable if the maximum scalar length is less than or equal to or strictly less than 1 mm. In some examples, for the modified protocol parameters to be determined to be acceptable, each component of the deformation vector field must be less than or equal to the distance corresponding to the resolution of the image. In some examples, for the modified protocol parameters to be determined to be acceptable, a threshold ratio of the scalar lengths of the x, y, and / or z components of the deformation vector field must be less than or equal to the distance corresponding to the resolution of the image.

[0083] A modified imaging protocol with acceptable modified protocol parameters can be considered geometrically accurate.

[0084] In some examples, for the acquired image acceptability check 300, it is not necessary to evaluate the entire acquired image or every pixel of the acquired image. Instead, the methods described herein can be used to evaluate a portion of the image or a portion of the pixels of the image to obtain the image acceptability check 300 and verify the corresponding portion of the image. The portion can be defined by a radius. The portion can correspond to a sub-image of a target for radiation therapy. The portion can correspond to a sub-image of the target and body contour information of the patient. Similarly, the threshold used by the acceptability check 300 can be determined by the intended purpose of the imaging, which may be only for visualizing a tumor, or may also require good visualization of one or more body contours, such as if the image is to be used for planning calculations.

[0085] A determination 306 as to whether the modified protocol parameters are acceptable may be output and / or stored 220. The modified protocol parameters may also be stored along with their respective determinations of acceptability to avoid repeating the method 200 when the same modified protocol parameters are received in the future. This may increase the efficiency of the method, reduce the computing resources required to perform the method, and may allow for the stored modified protocol parameters and their acceptability to be reviewed or not dependent on the performance of the method 200.

[0086] Aspects of the present method, including determining 306 whether modified protocol parameters are acceptable based at least in part on a similarity metric, facilitate evaluating modified protocol parameters to ensure that they do not adversely affect image quality or image acquisition functionality. Since the similarity metric between the acquired image and the verified image indicates the fidelity between the acquired image and the verified image, the modified protocol parameters can be identified as acceptable or unacceptable based on the degree of change between the acquired image and the verified image. Therefore, the present method can ensure that modified protocol parameters are accepted only when they do not result in adverse changes to the image or other unacceptable or suboptimal effects on image quality. Therefore, the disclosed method of modifying medical imaging protocol parameters allows for customization, modification, and optimization of imaging protocols while mitigating adverse effects on image quality or protocol performance that may be caused by unacceptable modified protocol parameters.

[0087] Additional or alternative measures may be implemented to validate or evaluate the modified protocol, including, for example, parameter acceptability checks. Figure 4 Depicted is a parameter acceptability check according to one aspect of a method 200 for modifying medical imaging protocol parameters. In this aspect, the method 200 includes: receiving 202 modified protocol parameters for an imaging protocol; and determining 204 whether the modified protocol parameters are acceptable based at least on a parameter acceptability check 400. The parameter acceptability check 400 includes identifying 402 whether the modified protocol parameter is one of the critical or performance parameters, and checking 404 the identified modified protocol parameter against a predetermined value.

[0088] The protocol can be modified only to a certain extent away from the validated protocol, for example by allowing modification of only a specific set of protocol parameters, or only allowing modification of protocol parameters within a specific range. This enables modification, customization and optimization of imaging protocols while limiting the scope of the modification, for example to avoid deviation from optimal performance or to ensure that the modified protocol parameters are compatible with the entire imaging protocol, especially for any parameters that are not modified.

[0089] In one aspect, the parameter acceptability check includes identifying 402 whether the modified protocol parameter is one of a critical or performance parameter. Acceptable modifications to the protocol parameter may depend on whether the modified protocol parameter is a critical parameter or a performance parameter. A critical parameter is a parameter corresponding to, for example, at least one of bandwidth, 3D geometric distortion, field of view, sound pressure level, and specific absorption rate (SAR). A performance parameter is a parameter corresponding to, for example, at least one of signal-to-noise ratio (SNR), contrast, body view, acquisition time, acquisition resolution, and fat suppression. The bandwidth parameter may affect the geometric fidelity of the acquired image. SAR indicates that the patient has fever (should be limited). The critical parameter may also correspond to one of the following: a parameter related to the rotation of the imaging stack; a parameter related to the use of acceleration techniques, such as sensitivity encoding (SENSE), generalized autocalibration partially parallel acquisition (GRAPPA), or compressed SENSE, particularly with high values; and / or a parameter related to a Cartesian or non-Cartesian readout type.

[0090] In some examples, a given key or performance parameter corresponds to a predetermined value or value range, and the acceptability of the modified protocol parameter is evaluated for the predetermined value or value range. When determining whether the modified protocol parameter is acceptable, the modified protocol parameter identified as one of the key or performance parameters is checked against the corresponding predetermined value. The predetermined value depends on factors including the identified modified protocol parameter, other modified protocol parameters, imaging protocols and / or unmodified protocol parameters. For example, the performance parameter SNR can be checked against a predetermined value of 10%, so that the SNR of the image acquired with the modified protocol is required to have an SNR parameter less than or equal to 10% in order to consider the modified protocol to be acceptable. The predetermined value can correspond to a key parameter value or performance parameter value of the verification image. The SNR can be maintained within 10% of the value of the verification image, that is, the difference is less than or equal to 10% of the value. In the exemplary performance of method 200, the modified signal-to-noise ratio is identified as a performance parameter, in particular a modified signal-to-noise ratio parameter, and is checked against the signal-to-noise ratio value of the verified image. The predetermined value or value range can be stored locally in the imaging device 112, a memory, or an online database.

[0091] In another example of one aspect of the method 200 involving a parameter acceptability check 400, the modified bandwidth is identified as a critical parameter and checked against a predetermined value. In one example, the predetermined value is 224 Hertz, which is a frequency typically used for a field strength of 1.5 T. In other words, the parameter acceptability check 400 checks whether the modified bandwidth parameter is greater than or equal to 224 Hz. This provides the advantage of ensuring that an imaging protocol with modified protocol parameters will reduce or prevent image distortion.

[0092] In some examples, the predetermined value may be a Boolean value, i.e., indicating whether the parameter is "true" or "false", or "selected" or "unselected". For example, checking 404 the key parameter 3D geometric distortion correction method for a predetermined value may include checking whether the 3D geometric distortion correction method is implemented, i.e., the parameter is "true" or "selected". This provides the advantage of ensuring that the imaging protocol with the modified protocol parameters will reduce and correct distortion.

[0093] Checking 404 the field of view against predetermined values ​​allows a parameter acceptability check 400 to ensure that the field of view covers the subject or portion of the subject to be imaged. This prevents wrapping or aliasing when acquiring images with modified protocol parameters.

[0094] In a further example of one aspect of the method 200 involving the parameter acceptability check 400, the modified sound pressure level is identified as a critical parameter and compared to a predetermined value corresponding to an upper limit. The upper limit is 110 dB(A). This improves the patient experience, particularly by ensuring that the imaging protocol with the modified protocol parameters does not cause uncomfortable or disturbing noise levels perceived by the patient.

[0095] In yet another example of the method 200, the SAR level is identified 402 as a key parameter and the key parameter is checked 404 against a predetermined value. This improves the patient experience, particularly by ensuring that an imaging protocol with modified SAR parameters does not create uncomfortable or unpleasant heat levels in or around the patient.

[0096] The parameter acceptability check according to the present disclosure can be used to further mitigate image artifacts, maintain and provide high image quality and optimal performance of the imaging system, and ensure the correct adaptation or recalculation of the treatment plan based on the acquired images. In addition, checking modified parameters such as sound pressure level and SAR can ensure a pleasant experience for the patient during image acquisition, thereby reducing anxiety and discomfort. The parameter acceptability check according to the present disclosure can also be applied to other image quality parameters, imaging device functional parameters, and / or radiotherapy system functional parameters known to those skilled in the art.

[0097] Additional advantages provided by various aspects of method 200 include the ability to modify imaging protocol parameters without placing additional mental or administrative load on the user of the imaging protocol. The user may be a clinician, optionally using an imaging protocol as part of a radiation therapy plan and / or clinical workflow. By enabling modification, customization, and optimization of imaging protocol parameters, imaging protocols specific to each patient and / or each workflow may be modified, customized, and optimized by modifying only the parameters that need to be modified while providing other necessary parameters or settings as part of the imaging protocol. This means that patient and / or workflow-specific protocols may be created without having to start from scratch each time. In addition, this minimizes the risk of user error or omission when modifying parameters.

[0098] Any examples of method 200 may also or alternatively be implemented in a workflow, or implemented using a device configured for functional imaging techniques. For example, for diffusion methods, using the image acceptability check and parameter acceptability check disclosed herein, modified protocol parameters such as b-values ​​can be verified to be within a specific range to mitigate any adverse effects on image quality. The method can also be implemented for use in connection with motion management images. The method can also be implemented to check the parameters of the functional map and compare these parameters with "validated" maps from a validated protocol. In this case, alternative / additional methods can be used, including analyzing the output of the image by using the image acceptability check and parameter acceptability check methods used herein to determine whether the apparent diffusion coefficient (ADC) values ​​are (sufficiently) similar and / or whether the motion estimates are (sufficiently) similar, so as to determine whether the modified protocol parameters are acceptable.

[0099] In some examples, in addition to or in lieu of the steps described herein, the method may include manual review of the registered image and the acquired image by a clinician to determine the similarity between the acquired image and the verified image. In other words, the acquired image acceptability check may include manual review of the acquired image by a clinician. For example, the clinician may determine whether the images are overlapping, and / or determine whether the degree of overlap is sufficient. This may be described as a manual assessment or determination of a similarity metric or geometric fidelity between the verified image and the acquired image. The clinician may also perform visual detection of artifacts in the verified and / or acquired images.

[0100] According to one aspect of the present disclosure, the method 200 according to any example described herein may further include performing artifact detection on at least one of the acquired image and the verified image in an artifact detection step 210. The artifact detection step 210 is performed to detect, locate and / or segment artifacts in at least one of the acquired image and the verified image, and thus includes detecting, locating and / or segmenting artifacts in at least one of the acquired image and the verified image. Additionally or alternatively, the artifact detection step 210 reports the image quality of at least one of the acquired image and the verified image. The reported image quality may be based at least in part on the detection, location and / or segmentation of artifacts in the acquired and / or verified images. The reported image quality may be used as part of an adjustment or recalculation of a treatment plan, or as part of a subsequent imaging workflow. The image quality may be reported using a qualitative scale, such as in percentage. The scale may be 0-100%, preferably 10%-100%. The scale may include a minimum or threshold image quality that the reported image quality must exceed in order for the image to be considered acceptable, such as in the range of 50%-100%, or preferably in the range of 70%-90%, or more preferably in the range of 75%-85%, or even more preferably a minimum threshold image quality of 80%. For each range, the endpoints are included so that, for example, a range of 50%-100% includes the values ​​of 50% and 100%.

[0101] In some examples, the artifact detection step 210 is performed by a computer vision tool. The computer vision tool can be based on a deep convolutional neural network and / or a conventional image processing algorithm, and can be trained to detect, locate and / or segment artifacts present in the image. In other words, the computer vision tool performs a method of artifact detection, location and / or segmentation on the image. The computer vision tool is programmed and used to detect, locate and / or segment artifacts in at least one of the acquired image and the verified image, and can also report the probability of the presence of artifacts in the image. Additionally or alternatively, the computer vision tool can report image quality, which can be based at least in part on the detected, located and / or segmented artifacts. Image quality can be reported in a qualitative scale, such as a percentage. The computer vision tool can be arranged to detect, locate and / or segment artifacts based on comparing at least one of the acquired image and the verified image with a template or reference image of the artifact, so as to assess whether the artifact associated with the template or reference image is present in at least one of the acquired image and the verified image.

[0102] In one aspect, the computer vision tool, for example, suggests or outputs alternative modified protocol parameters based at least in part on the reported image quality of at least one of the acquired image and the verified image. In particular, if the reported image quality of the acquired image is below a threshold quality (e.g., 80%), the computer vision tool prompts the user to reacquire the image using different parameters, different sequence selections, and / or different actions from the clinician to reduce or mitigate the detected artifacts. Therefore, the computer vision tool acts as an additional quality assurance measure. In examples where the computer vision tool cannot suggest different parameters, sequence selections, or clinician actions to adequately reduce or mitigate artifacts, or in addition to these suggestions, the computer vision tool can provide or suggest alternative clinical methods to eliminate any harmful effects of artifacts on the imaging workflow. This will be particularly effective for artifact sources, including but not limited to body motion, respiratory motion, metal implants, and / or excessive radial streaks of the patient. For example, in order to minimize the patient's large amount of motion, the computer vision tool can instruct the clinician to calm the patient and ask them to try to stay still. In some examples, to minimize or accommodate the patient's respiratory motion, the computer vision tool may instruct the clinician to retry image acquisition while implementing respiratory guidance. The clinician may be, for example, a radiologic technician. In some examples, to minimize artifacts caused by metal implants, the computer vision tool may suggest using spin echo instead of gradient echo images, thereby reducing signal loss. In some examples, to minimize or prevent excessive radial streaks, the computer vision tool may suggest acquiring a 3D VANE with more streaks.

[0103] In addition to the advantages provided by the examples of the methods described herein, computer vision tools can provide various advantages. The tool performs artifact detection, provides automated image quality checks, effectively reduces image artifacts or provides workflow-specific guidance on how to reduce image artifacts, reduces the risk of incorrect adaptation or recalculation of treatment plans due to image artifacts, and can improve the patient experience. The computer vision tool reduces the workload of the clinician because there is no need to manually review the images to look for artifacts, or determine an alternative protocol to reduce artifacts.

[0104] According to any of the examples described herein, the computer vision tool may be used to determine 204 whether the modified protocol parameters are acceptable in various aspects of the method 200 in one or both of the acquired image acceptability check 300 or the parameter acceptability check 400. The computer vision tool may also be used in any other steps of the method 200 described herein. The alternative protocol parameters suggested or output by the computer vision tool according to any of the examples described herein may be based at least in part on at least one of the acquired image acceptability check 300 and the parameter acceptability check 400.

[0105] Optionally as part of a clinical workflow, a method for medical image acquisition may include a method 200 for modifying medical imaging protocol parameters according to any embodiment described herein. The method for image acquisition may further include, in the case where the modified protocol parameters are determined to be acceptable, using a protocol with acceptable modified protocol parameters to acquire subsequent images. In an example where the medical imaging is MR imaging, the method includes acquiring MR images using a protocol with acceptable modified protocol parameters. In other examples, such as an example where the medical imaging is CT imaging, the method includes acquiring CT images using a protocol with acceptable modified protocol parameters. In the case where the modified protocol parameters are determined to be unacceptable, the image acquisition method may also include one or more of the following steps: receiving an alternative modified protocol parameter for the imaging protocol, for example, an alternative modified protocol parameter output by or from a computer vision tool; acquiring subsequent images of the subject using the protocol with the alternative modified parameters; and determining whether the alternative modified protocol parameters are acceptable based on at least one of an acquired image acceptability check and a parameter acceptability check. The computer vision tool may also be used according to any example in the method for medical image acquisition. For example, a computer vision tool can be used to detect, locate and / or segment artifacts in an artifact detection step in subsequent images acquired using alternative modified protocol parameters. The computer vision tool can report the image quality of subsequent acquired images and / or suggest or output further replaceable modified protocol parameters or clinician directions based at least in part on the reported quality of the subsequently acquired images and / or the verified images. The method can be repeated, outputting or suggesting further replaceable modified parameters, until it is determined that the modified protocol parameters are acceptable. The clinical workflow can include a method 200 for modifying medical imaging protocol parameters and / or a method for medical image acquisition as described herein.

[0106] Figure 5 Depicted is a block diagram of one implementation of a radiation therapy system 500. The radiation therapy system 500 includes a computing system 510 within which a set of instructions may be executed for causing the computing system 510 to perform any one or more of the methodologies discussed herein.

[0107] Computing system 510 should be considered to include any number or set of machines, such as executing one group (or multiple groups) of instructions to perform any one or more computing devices in the method discussed herein, either individually or jointly. That is, hardware and / or software can be provided in a single computing device, or distributed on multiple computing devices in a computing system. In some implementations, one or more elements of a computing system can be connected (e.g., networked) to other machines, such as in a local area network (LAN), an intranet, an extranet, or the Internet. One or more elements of a computing system can operate with the capacity of a server or client machine in a client-server network environment, or as a peer-to-peer machine operation in a peer-to-peer (or distributed) network environment. One or more elements of a computing system can be a personal computer (PC), a tablet computer, a set-top box (STB), a personal digital assistant (PDA), a cellular phone, a network device, a server, a network router, a switch or a bridge, or any machine that can perform an instruction set (sequential or other) specifying the action to be taken by the machine.

[0108] The computing system 510 includes a controller circuit 511 and a memory 513 (e.g., a read-only memory (ROM), a flash memory, a dynamic random access memory (DRAM) such as a synchronous DRAM (SDRAM) or a Rambus DRAM (RDRAM), etc.). The memory 513 may include a static memory (e.g., a flash memory, a static random access memory (SRAM), etc.) and / or an auxiliary memory (e.g., a data storage device) that communicate with each other through a bus (not shown).

[0109] Controller circuit 511 represents one or more general-purpose processors, such as microprocessors, central processing units, accelerated processing units, etc. More specifically, controller circuit 511 may include complex instruction set computing (CISC) microprocessors, reduced instruction set computing (RISC) microprocessors, very long instruction words (VLIW) microprocessors, processors that implement other instruction sets, or processors that implement instruction set combinations. Controller circuit 511 may also include one or more special processing devices, such as application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), digital signal processors (DSPs), network processors, etc. One or more processors of the controller circuit may have a multi-core design. Controller circuit 511 is configured to execute processing logic for executing the operations and steps discussed herein.

[0110] The computing system 510 may also include a network interface circuit 518. The computing system 510 may be communicatively coupled to an input device 520 and / or an output device 530 via an input / output circuit 517. In some implementations, the input device 520 and / or the output device 530 may be elements of the computing system 510. The input device 520 may include an alphanumeric input device (e.g., a keyboard or a touch screen), a cursor control device (e.g., a mouse or a touch screen), an audio device (e.g., a microphone), a graphical user interface (GUI), and / or a tactile input device. The output device 530 may include an audio device, such as a speaker, a video display unit (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)), and / or a tactile output device. In some embodiments, the input device 520 and the output device 530 may be provided as a single device or as separate devices. The input device 520 may be used to input modified protocol parameters. In other words, the modified protocol parameters may be input at the input device 520 and / or the input device 520 may be configured to receive the modified protocol parameters.

[0111] In some implementations, the computing system 510 includes a training circuit 518. The training circuit 518 is configured to train a method for detecting, locating, and / or segmenting artifacts in MR images. For example, the training circuit 518 can train a model for performing a method for detecting, locating, and / or segmenting artifacts in MR images. The training circuit 518 can also train a model for suggesting imaging protocol parameters, sequence selection, and / or clinician actions based at least in part on detected image artifacts. The model can include a deep neural network (DNN), such as a convolutional neural network (CNN) and / or a recurrent neural network (RNN). The training circuit 518 can be configured to execute instructions to train a model that can be used to detect, locate, and / or segment image artifacts in MR. The training circuit 518 can also be configured to execute instructions to train a model that can suggest imaging protocol parameters, sequence selection, and / or clinician actions based at least in part on detected image artifacts. Training methods for training such models will be known to technicians. The training circuitry 518 may be configured to access training data and / or test data from the memory 513 or from a remote data source, for example, via the network interface circuitry 515. In some examples, the training data and / or test data may be obtained from an external component such as the image acquisition device 540 and / or the treatment device 550. In some implementations, the training circuitry 518 may be used to update, validate, and / or maintain a model for detecting, localizing, and / or segmenting image artifacts in MR images. In some implementations, the training circuitry 518 may also be used to update, validate, and / or maintain a model for suggesting imaging protocol parameters, sequence selections, and / or clinician actions based at least in part on detected image artifacts.

[0112] In some implementations, the computing system 510 may include an image processing circuit 519. The image processing circuit 519 may be configured to process image data 580 (e.g., images or imaging data), such as medical images obtained from one or more imaging data sources, treatment devices 550, and / or image acquisition devices 540. The image processing circuit 519 may be configured to process or pre-process the image data. For example, the image processing circuit 519 may convert the received image data into a specific format, size, resolution, etc. In some implementations, the image processing circuit 519 may be combined with the controller circuit 511. The image processing circuit 519 may be configured to process the image data according to any example of the method 200 described herein. For example, in some examples, the image processing circuit 519 may be configured for an acquired image acceptability check, a structured similarity index metric technique, and / or a normalized cross-correlation. The image processing circuit 519 may be configured to determine whether the modified protocol parameters are acceptable based on at least one of an acquired image acceptability check and a parameter acceptability check.

[0113] In some embodiments, the radiation therapy system 500 may also include an image acquisition device 540 and / or a treatment device 550. The image acquisition device 540 and the treatment device 550 may be provided as a single device. In some implementations, the treatment device 550 is configured to perform imaging, for example in addition to providing treatment and / or during treatment. The treatment device 550 includes the main radiation delivery components of the radiation therapy system, such as a linear accelerator.

[0114] The image acquisition device 540 can be configured to perform magnetic resonance imaging (MRI), and can also or alternatively be configured to perform positron emission tomography (PET) or computed tomography (CT). In examples where the image acquisition device 540 is configured to perform positron emission tomography, the methods disclosed herein can be applied to PET imaging and images. In examples where the image acquisition device 540 is configured to perform CT imaging, the methods disclosed herein can be applied to CT imaging and images. In other examples, the image acquisition device 540 is configured to perform one or more of portal imaging, cone beam CT, and / or SPECT imaging, and the methods disclosed herein can be applied to the corresponding imaging modalities.

[0115] Image acquisition device 540 may be configured to output image data 580, which may be accessed by computing system 510. Treatment device 550 may be configured to output treatment data 560, which may be accessed by computing system 510.

[0116] The computing system 510 can be configured to access or obtain treatment data 560, planning data 570, and / or image data 580. The treatment data 560 can be obtained from an internal data source (e.g., from the memory 513) or from an external data source (e.g., the treatment device 550 or an external database). The planning data 570 can be obtained from the memory 513 and / or from an external source such as a planning database. The planning data 570 may include information obtained from one or more of the image acquisition device 540 and the treatment device 550. The computer system 510 can use at least one of the image data, the treatment data, and / or the planning data to adjust or recalculate the treatment plan. The input device 520 can also be configured to receive and / or be used to input the treatment data 560 and / or the planning data 570.

[0117] The various methods described above may be implemented by a computer program. The computer program may include computer code (e.g., instructions) 610, which is arranged to instruct a computer to perform the functions of one or more of the various methods described above. The steps of the methods described above may be performed in any suitable order. For example, the artifact detection step 210 of method 200 may be performed before, after, simultaneously, or substantially simultaneously with step 220. The acquired image acceptability check according to step 300 may be performed before, after, simultaneously, or substantially simultaneously with the parameter acceptability check according to step 400. The computer program and / or code 610 for performing this method may be on one or more computer readable media or more generally on a computer readable medium. Figure 6 The computer program product 600 shown is provided to a device such as a computer. The computer readable medium can be temporary or non-temporary. One or more computer readable media 600 can be, for example, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, or a propagation medium for data transmission, such as for downloading code on the Internet. Alternatively, the one or more computer readable media can take the form of one or more physical computer readable media such as semiconductor or solid-state memory, magnetic tape, removable computer floppy disk, random access memory (RAM), read-only memory (ROM), rigid disk and optical disk (such as CD-ROM, CD-R / W or DVD). The instructions 610 can also reside completely or at least partially in the memory 513 and / or in the controller circuit 511 during execution by the computing system 510, and the memory 513 and the controller circuit 511 also constitute computer readable storage media.

[0118] In one implementation, the modules, components, and other features described herein may be implemented as discrete components or integrated in the functionality of hardware components such as an ASIC, FPGA, DSP, or similar device.

[0119] A "hardware component" is a tangible (e.g., non-transitory) physical component (e.g., one or more processor groups) that is capable of performing specific operations and may be configured or arranged in a specific physical manner. A hardware component may include dedicated circuitry or logic that is permanently configured to perform certain operations. A hardware component may include a dedicated processor, such as an FPGA or ASIC. A hardware component may also include programmable logic or circuitry that is temporarily configured by software to perform certain operations.

[0120] In addition, modules and components can be implemented as firmware or functional circuits within hardware devices. In addition, modules and components can be implemented in any combination of hardware devices and software components, or only in software (e.g., code stored in a machine-readable medium or in a transmission medium or otherwise embodied).

[0121] Unless otherwise noted, as will be apparent from the following discussion, throughout the description, discussions using terms such as "receiving," "determining," "examining," "aligning," "evaluating," "suggesting," "verifying," "evaluating," "outputting," "storing," "obtaining," "providing," and the like refer to the actions and processes of a computer system, or similar electronic computing device, that manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data represented as physical quantities within the computer system's memories or registers, or other such information storage, transmission, or display devices.

[0122] It should be understood that the above description is intended to be illustrative rather than restrictive. For those skilled in the art, after reading and understanding the above description, many other implementations will be clear. Although the present disclosure has been described with reference to specific example implementations, it will be appreciated that the present disclosure is not limited to the described implementations, but can be practiced by modification and change within the spirit and scope of the appended claims. In particular, the features and steps described herein can be combined in any arrangement and in any order. Therefore, the description and drawings should be regarded as illustrative rather than restrictive. Therefore, the scope of the present disclosure should be determined with reference to the appended claims and the full scope equivalent to these claims.

Claims

1. A computer-implemented method for modifying medical imaging protocol parameters, comprising: receiving modified protocol parameters for an imaging protocol; as well as A determination is made whether the modified protocol parameters are acceptable based on at least one of an acquired image acceptability check and a parameter acceptability check.

2. The method according to claim 1, characterized in that Also included is updating protocol parameters based on the modified protocol parameters.

3. The method according to claim 1, characterized in that: Also included is outputting and / or storing a determination of whether the modified protocol parameters are acceptable.

4. The method according to claim 1, characterized in that: The acquired image acceptability check includes: acquiring images of the subject using the protocol having the modified protocol parameters; determining a similarity measure between the acquired image and the verified image; and A determination is made whether the modified protocol parameters are acceptable based at least in part on the similarity metric.

5. The method according to claim 4, characterized in that The similarity measure is associated with a geometric transformation between the acquired image and the verified image.

6. The method according to claim 5, characterized in that The geometric transformation includes a deformation vector field.

7. The method according to claim 6, characterized in that Determining the geometric transformation comprises determining at least one of the x, y and / or z displacement components of the deformation vector field and / or a scalar length of at least one of the displacement components.

8. The method according to claim 6 or 7, characterized in that: Determining whether the modified protocol parameters are acceptable is based at least in part on at least one of the x, y, and / or z displacement components of the deformation vector field and / or a scalar length of at least one of the displacement components.

9. The method according to claim 7, characterized in that: If the scalar length of the threshold ratio of the x, y and / or z displacement components is less than or equal to a maximum scalar length, then the modified protocol parameters are determined to be acceptable.

10. The method according to claim 9, characterized in that The threshold ratio is in the range of 60% to 100%, preferably the threshold ratio is in the range of 80% to 100%, more preferably the threshold ratio is in the range of 90% to 100%, even more preferably the threshold ratio is about 95%.

11. The method according to claim 9 or 10, characterized in that: The maximum scalar length is in the range of 0.5 mm to 4 mm, preferably the maximum scalar length is in the range of 1.5 mm to 2.5 mm, and more preferably the maximum scalar length is about 2 mm.

12. The method according to claim 9 or 10, characterized in that: The maximum scalar length is based on the resolution of the verified image.

13. The method according to any one of claims 5 to 7, characterized in that Determining a geometric transformation between the acquired image and the verified image includes attempting to register the acquired image with the verified image.

14. The method according to claim 13, characterized in that If the attempt to register the acquired image with the verified image is unsuccessful and / or a geometric transformation cannot be determined, then the modified protocol parameters are determined to be unacceptable.

15. The method according to any one of claims 5 to 7, characterized in that The validated images are acquired using an imaging protocol having unmodified or validated protocol parameters.

16. The method according to any one of claims 4 to 7, characterized in that The similarity metric value is associated with a structural similarity index metric or a normalized cross-correlation metric between the acquired image and the verified image.

17. The method according to claim 1, characterized in that The parameter acceptability check includes identifying whether the modified protocol parameter is a critical parameter or a performance parameter, and checking the identified modified protocol parameter against a predetermined value.

18. The method according to claim 17, characterized in that Identifying whether the modified protocol parameter is a critical parameter includes identifying whether the modified protocol parameter corresponds to at least one of bandwidth, 3D geometric distortion, field of view, sound pressure level, and / or specific absorption rate.

19. The method according to claim 17 or 18, characterized in that Identifying whether the modified protocol parameter is a performance parameter includes identifying whether the modified protocol parameter corresponds to at least one of signal-to-noise ratio, contrast, body view, acquisition time, acquisition resolution, and / or fat suppression.

20. The method according to claim 1, characterized in that Also includes: A determination of whether the modified protocol parameters are acceptable is output and / or stored, and optionally the modified protocol parameters and the determination thereof are stored.

21. The method according to claim 1, characterized in that The modified protocol parameters are received from a user input device.

22. The method according to claim 1, characterized in that Also includes: Perform artifact detection on the acquired images.

23. The method according to claim 22, characterized in that Performing the artifact detection includes detecting, locating, and / or segmenting artifacts in at least one of the acquired image and the verified image.

24. The method according to claim 22 or 23, characterized in that Performing the artifact detection includes reporting image quality of at least one of the acquired image and the verified image.

25. The method according to claim 24, characterized in that The computer vision tool outputs replacement modified protocol parameters based at least in part on the reported image quality of the acquired image and / or the verified image.

26. A method for obtaining a medical image, comprising: A method for modifying medical imaging protocol parameters as claimed in any preceding claim; wherein if the modified protocol parameters are determined to be acceptable, a subsequent image is acquired using a protocol having the acceptable modified protocol parameters.

27. The method according to claim 26, characterized in that The medical imaging is magnetic resonance imaging.

28. A computer readable medium comprising computer executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 27.

29. A system for medical imaging, comprising: Medical imaging devices; processor; and A computer readable medium comprising computer executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 27.

30. A radiotherapy apparatus comprising the system for medical imaging according to claim 29.

Images