Methods and systems for assisted diagnostic scan acquisition
By generating difference images to detect motion and offering an assisted scan acquisition mode, the CT system addresses false triggers, ensuring accurate and efficient scan initiation with reduced X-ray exposure.
Patent Information
- Application Number
- JP2024067120
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-04
- Filing Date
- 2024-04-18
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-04-18
AI Technical Summary
Existing CT imaging systems face challenges in robustly initiating diagnostic scans due to false triggers from subject movement and contrast agent changes, leading to inefficient scan acquisition and increased X-ray exposure.
The system generates a difference image from initial and subsequent CT images to detect motion outside the region of interest (ROI) and provides an assisted scan acquisition mode, allowing operators to override automatic initiation based on visual or machine learning analysis, ensuring accurate scan timing.
This approach enhances scan acquisition robustness by reducing false triggers, improving image quality, and minimizing subject exposure to X-rays while maintaining efficient workflow.
Smart Images

Figure 2024160949000001_ABST
Abstract
Description
[Technical field]
[0001] FIELD OF THE DISCLOSURE Embodiments of the subject matter disclosed herein relate to acquiring X-ray images, and in particular computed tomography images. [Background technology]
[0002] Computed tomography (CT) can be used as a non-invasive medical imaging technique. Specifically, CT imaging data acquisition can include passing an X-ray beam through an object, such as a patient, such that the X-ray beam is attenuated, and collecting the attenuated X-ray beam with an X-ray detector array. This allows imaging of various tissues, including bone, soft tissue, etc., as well as high contrast detection, which allows the CT imaging system to visualize contrast agents.
[0003] In instances where contrast agents are used, the CT imaging system may be configured to automatically detect changes in image contrast within a monitored region of interest (ROI). In response to a change in contrast exceeding a threshold, acquisition of a diagnostic scan may be automatically initiated. In some embodiments, motion in and / or near the ROI may trigger early or late acquisition of a diagnostic scan relative to an instance of an actual change in contrast reaching a threshold. Summary of the Invention
[0004] In one embodiment, the x-ray imaging system includes generating a difference image from the first image and the second image and displaying the difference image on a display device in response to operation of the x-ray imaging system in an automatic mode. By displaying the image on the display device, motion outside a region of interest (ROI) may be detected based on analysis of the difference image. The difference image may be displayed before the contrast agent reaches the ROI. In this manner, automatic initiation of diagnostic scan acquisition may be assisted by an optional process for triggering diagnostic scan acquisition if motion is present outside the ROI. Initiation of diagnostic scan acquisition may thereby be more robust against motion that may otherwise cause false triggering of scan acquisition. As a result, diagnostic information about a subject may be obtained more efficiently while reducing x-ray exposure of the subject.
[0005] It should be appreciated that the above brief description is provided to introduce in a simplified form some of the concepts that are further described in the detailed description. It is not intended to identify key features or essential features of the claimed subject matter, the scope of which is defined solely by the claims that follow the detailed description. Moreover, the claimed subject matter is not limited to implementations that solve the disadvantages noted above or in any part of this disclosure. [Brief description of the drawings]
[0006] The invention will be better understood from reading the following description of non-limiting embodiments, with reference to the accompanying drawings, in which: [Figure 1] FIG. 1 is a pictorial diagram illustrating an imaging system according to one embodiment. [Diagram 2] 1 is a block schematic diagram of an exemplary imaging system in accordance with an embodiment. [Diagram 3] 1 illustrates a scout image acquired by a CT imaging system, according to an embodiment. [Figure 4] 3 illustrates a first cross-sectional image acquired by a CT imaging system based on the scout image of FIG. 2, according to an embodiment. [Diagram 5] 3 illustrates a second cross-sectional image acquired by a CT imaging system based on the scout image of FIG. 2, according to an embodiment. [Figure 6] 1 shows a first difference image according to an embodiment. [Figure 7] 13 illustrates a second difference image according to an embodiment. [Figure 8] 1 illustrates a high level workflow for scan acquisition assistance in a CT imaging system, according to an embodiment. [Figure 9] 1 is a graph plotting contrast in a region of interest of a difference image, according to an embodiment; [Figure 10] 1 illustrates a display presented to an operator during assisted scan acquisition in a CT imaging system, according to one embodiment. [Figure 11A] 1 illustrates a method of acquiring CT images using a CT imaging system configured with assisted scan acquisition, according to one embodiment. [Figure 11B] 1 illustrates a method of acquiring CT images using a CT imaging system configured with assisted scan acquisition, according to one embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0007] The following description relates to various embodiments of diagnostic scan acquisition assistance in an X-ray imaging system. More specifically, diagnostic scan acquisition may be automatically triggered and modified in a CT system based on detection of motion in a region of interest (ROI). An example of a CT system is shown in FIG. 1, and a block schematic diagram of the components of the CT system is shown in FIG. 2. During a diagnostic event, a scout image may be acquired first to orient the CT system. The scout image may then be used as a guide to obtain cross-sectional images focused on the region of interest (ROI), examples of which are depicted in FIGS. 4-5. To determine the mode of scan acquisition initiation to be performed in the CT system, a difference image may be generated to determine whether there is motion around the ROI. Examples of difference images are shown in FIGS. 6-7. The difference image may be used to select a mode of scan acquisition initiation according to the high-level workflow shown in FIG. 8, where a scan acquisition assistance may be performed if motion is detected. In the early stages of scan acquisition, the contrast difference in the cross-sectional images acquired by the CT system may be monitored, as depicted in the graph of Figure 9, and this difference may be displayed to the operator along with the CT image, as shown in Figure 10. An example of a method for acquiring a CT image by assisted scan photography is shown in Figures 11A to 11B.
[0008] Before further describing approaches for assisting scan acquisition, a general overview of CT imaging is provided. FIG. 1 illustrates an exemplary CT system 100 configured for CT imaging. In particular, the CT system 100 is configured to image a subject 112, such as a patient, an inanimate object, one or more manufactured parts, and / or foreign objects such as dental implants, stents, and / or contrast agents present in the body. In one embodiment, the CT system 100 includes a gantry 102, which may further include at least one X-ray source 104 configured to project an X-ray radiation beam 106 (see FIG. 2 ) for use in imaging the subject 112 lying on a table 114. In particular, the X-ray source 104 is configured to project the X-ray radiation beam 106 toward a detector array 108 disposed on the opposite side of the gantry 102. Although only a single X-ray source 104 is depicted in FIG. 1, in certain embodiments, multiple X-ray sources and detectors can be employed to project multiple X-ray radiation beams 106 for acquiring projection data at different energy levels corresponding to the patient. In some embodiments, the X-ray source 104 can enable dual energy gemstone spectral imaging (GSI) with rapid peak kilovoltage (kVp) switching. In some embodiments, the X-ray detector employed is a photon counting detector capable of distinguishing between X-ray photons of different energies. In other embodiments, two sets of X-ray sources and detectors are used to generate dual energy projections, one at low kVp and the other at high kVp. Thus, it should be understood that the methods described herein can be implemented with single energy collection techniques as well as dual energy collection techniques.
[0009] In certain embodiments, the CT system 100 further includes an image processor unit 110 configured to reconstruct an image of the target volume of the object 112 using an iterative or analytical image reconstruction method. For example, the image processor unit 110 can use an analytical image reconstruction technique, such as filtered back projection (FBP), to reconstruct an image of the target volume of the patient. As another example, the image processor unit 110 can reconstruct an image of the target volume of the object 112 using an iterative image reconstruction approach, such as advanced statistical iterative reconstruction (ASIR), conjugate gradient (CG), maximum likelihood expectation maximization (MLEM), model-based iterative reconstruction (MBIR), etc. As described further herein, in some examples, the image processor 110 can use both an analytical image reconstruction approach, such as FBP, in addition to an iterative image reconstruction approach.
[0010] In some CT imaging system configurations, an x-ray source projects a cone-shaped beam of x-ray radiation that is collimated to lie in an XYZ plane of a Cartesian coordinate system and is commonly referred to as an "imaging plane." The x-ray radiation beam passes through an imaging object, such as a patient or subject. The x-ray radiation beam, after being attenuated by the object, impinges on an array of detector elements. The intensity of the attenuated x-ray radiation beam received at the detector array depends on the attenuation of the radiation beam by the object. Each detector element of the array produces a separate electrical signal that is a measurement of the attenuation of the x-ray beam at the detector location. Attenuation measurements from all detector elements are acquired separately to produce a transmission profile.
[0011] In some CT systems, the x-ray source and detector array are rotated with the gantry in the imaging plane and around the object being imaged such that the angle at which the radiation beam intersects the object is constantly changing. A set of x-ray radiation attenuation measurements, e.g., projection data, from the detector array at a gantry angle is called a "view." A "scan" of an object includes a series of views made at different gantry angles, i.e., view angles, during one revolution of the x-ray source and detector. As used herein, the term "view" is not limited to the use described above with respect to projection data from one gantry angle, since it is contemplated that the benefits of the methods described herein may accrue to medical imaging modalities other than CT. The term "view" is used to mean one data acquisition whenever there are multiple data acquisitions from different angles, whether from CT, Positron Emission Tomography (PET) imaging, or Single Photon Emission CT (SPECT) imaging, and / or other modalities including modalities yet to be developed, as well as combinations thereof in fused embodiments.
[0012] The projection data is processed to reconstruct an image corresponding to a two-dimensional slice through the object, and in some instances where the projection data includes multiple views or scans, a three-dimensional rendering of the object is reconstructed. One method for reconstructing an image from a set of projection data is referred to in the art as filtered backprojection. Transmission and emission tomography reconstruction techniques also include statistical iterative methods such as maximum likelihood expectation maximization (MLEM) and ordered-subsets expectation-reconstruction techniques, as well as iterative reconstruction techniques. This process converts the attenuation measurements from the scan into integers called "CT numbers" or "Hounsfield units," which are used to control the brightness of the corresponding pixels on a display device.
[0013] To reduce the total scan time, a "helical" scan may be performed by moving the patient while acquiring data for a given number of slices. In such a system, a single helix is generated from a cone beam helical scan. The helix mapped by the cone beam produces projection data from which images for each given slice may be reconstructed.
[0014] As used herein, the phrase "reconstructing an image" is not intended to exclude embodiments of the invention in which data representative of an image is generated, but a viewable image is not generated. Thus, as used herein, the term "image" refers broadly to both a viewable image and data representing a viewable image. However, many embodiments generate (or are configured to generate) at least one viewable image.
[0015] FIG. 2 illustrates an exemplary imaging system 200 similar to the CT system 100 of FIG. 1. In accordance with aspects of the present disclosure, the imaging system 200 is configured to image an object 204 (e.g., object 112 of FIG. 1). In one embodiment, the imaging system 200 includes a detector array 108 (see FIG. 1). The detector array 108 further includes a plurality of detector elements 202 that together sense an X-ray radiation beam 106 (see FIG. 2) passing through the object 204 (e.g., a patient) to obtain corresponding projection data. Thus, in one embodiment, the detector array 108 is fabricated in a multi-slice configuration that includes multiple columns of cells or detector elements 202. In such a configuration, one or more additional rows of detector elements 202 are arranged in a parallel configuration to obtain projection data.
[0016] In certain embodiments, the imaging system 200 is configured to traverse different angular positions around the object 204 to acquire the desired projection data. Thus, the gantry 102 and the components mounted thereon may be configured to rotate about a center of rotation 206 to acquire projection data at different energy levels, for example. Alternatively, in embodiments in which the projection angle relative to the object 204 changes as a function of time, the mounted components may be configured to move along a general curve rather than along a segment of a circle.
[0017] As the x-ray source 104 and detector array 108 rotate, the detector array 108 collects data of the attenuated x-ray beam. The data collected by the detector array 108 undergoes pre-processing and calibration to condition the data to represent line integrals of the attenuation coefficients of the scanned object 204. The processed data are commonly referred to as projections.
[0018] In some examples, individual detectors or detector elements 202 of the detector array 108 may include photon-counting detectors that register interactions of individual photons into one or more energy bins. It should be understood that the methods described herein may also be implemented with energy-integrating detectors.
[0019] The acquired set of projection data can be used for basis material decomposition (BMD). During BMD, the measured projections are converted into a set of material density projections. The material density projections can be reconstructed to form a set or set of material density maps or images of each basis material, such as bone, soft tissue, and / or contrast agent maps. The density maps or images can then be related to form a volume rendering of the basis materials, e.g., bone, soft tissue, and / or contrast agent, within the imaged volume.
[0020] Once reconstructed, the basis material image produced by the imaging system 200 reveals internal features of the subject 204, represented by the densities of the two basis materials. The density image can be displayed to show these features. In a conventional approach to the diagnosis of a medical condition, such as a medical condition, or more generally a medical event, a radiologist or physician considers a hard copy or display of the density image to identify characteristic features of interest. Such features include lesions, the size and shape of a particular anatomical structure or organ, and other features identifiable from the image based on the skill and knowledge of the individual physician.
[0021] In one embodiment, the imaging system 200 includes a control mechanism 208 that controls the movement of components such as the rotation of the gantry 102 and the operation of the X-ray source 104. In some embodiments, the control mechanism 208 further includes an X-ray controller 210 configured to provide power and timing signals to the X-ray source 104. Additionally, the control mechanism 208 includes a gantry motor controller 212 configured to control the rotational speed and / or position of the gantry 102 based on the imaging requirements.
[0022] In certain embodiments, the control mechanism 208 further includes a data acquisition system (DAS) 214 configured to sample analog data received from the detector elements 202 and convert the analog data to a digital signal for subsequent processing. The DAS 214 may be further configured to selectively aggregate analog data from a subset of the detector elements 202 into a so-called macro-detector, as further described herein. The data sampled and digitized by the DAS 214 is transmitted to a computer or computing device 216. In one example, the computing device 216 stores the data in a storage device or mass storage device 218. The storage device 218 may include, for example, a hard disk drive, a floppy disk™ drive, a compact disk read / write (CD-R / W) drive, a digital versatile disk (DVD) drive, a flash drive, and / or a solid-state storage drive.
[0023] Additionally, computing device 216 provides commands and parameters to one or more of DAS 214, X-ray controller 210, and gantry motor controller 212 to control system operations, such as data acquisition and / or processing. In certain embodiments, computing device 216 controls system operations based on operator input. Computing device 216 receives operator input, including commands and / or scanning parameters, for example, via an operator console 220 operably coupled to computing device 216. Operator console 220 may include a keyboard (not shown) or a touch screen to enable an operator to specify commands and / or scanning parameters.
[0024] In some examples, as described herein, the computing device 216 may be configured with instructions, e.g., algorithms, for initiating acquisition of a diagnostic scan in response to a trigger according to an automatic scan acquisition mode. The trigger, in one example, may be a change in image contrast by at least a threshold amount corresponding to detection of contrast agent in the ROI. The instructions may also enable detection of motion near the ROI (e.g., an area surrounding the ROI), which may prompt an option to initiate acquisition according to an auxiliary scan acquisition mode presented to the operator. Further details of the automatic scan acquisition mode and the assisted scan acquisition mode are provided further below with reference to FIGS. 3-11.
[0025] 2, multiple operator consoles may be coupled to the imaging system 200, e.g., for inputting or outputting system parameters, requesting examinations, plotting data, and / or viewing images. Additionally, in certain embodiments, the imaging system 200 may be coupled to multiple displays, printers, workstations, and / or similar devices located either locally or remotely, e.g., within an institution or hospital, or at an entirely different location, via one or more configurable wired and / or wireless networks, such as the Internet and / or a virtual private network, a wireless telephone network, a wireless local area network, a wired local area network, a wireless wide area network, a wired wide area network, etc.
[0026] In one embodiment, for example, imaging system 200 includes or is coupled to a picture archiving and communications system (PACS) 224. In an exemplary implementation, PACS 224 is further coupled to remote systems, such as a radiology department information system, a hospital information system, and / or an internal or external network (not shown), allowing operators at different locations to provide commands and parameters and / or access image data.
[0027] Using operator-supplied and / or system-defined commands and parameters, the computing device 216 operates a table motor controller 226, which may control the table 114, which may be a motorized table. In particular, the table motor controller 226 may move the table 114 to properly position the subject 204 within the gantry 102 to acquire projection data corresponding to a target volume of the subject 204.
[0028] As mentioned above, the DAS 214 samples and digitizes the projection data acquired by the detector elements 202. The image reconstructor 230 then performs high speed reconstruction using the sampled and digitized x-ray data. Although FIG. 2 illustrates the image reconstructor 230 as a separate entity, in certain embodiments, the image reconstructor 230 may form part of the computing device 216. Alternatively, the image reconstructor 230 may not be present in the imaging system 200, and instead the computing device 216 may perform one or more functions of the image reconstructor 230. Furthermore, the image reconstructor 230 may be located locally or remotely and may be operably connected to the imaging system 200 using a wired or wireless network. In particular, in an exemplary embodiment, computing resources in a "cloud" network cluster may be used for the image reconstructor 230.
[0029] In one embodiment, the image reconstructor 230 stores the reconstructed image in the storage device 218. Alternatively, the image reconstructor 230 may transmit the reconstructed image to the computing device 216 for generating patient information useful for diagnosis and evaluation. In certain embodiments, the computing device 216 may transmit the reconstructed image and / or the patient information to a display or display device 232 communicatively coupled to the computing device 216 and / or the image reconstructor 230. In some embodiments, the reconstructed image may be transmitted from the computing device 216 or the image reconstructor 230 to the storage device 218 for short-term or long-term storage.
[0030] Various methods and processes described further herein (such as those described below with reference to FIGS. 11A-11B) may be stored as executable instructions in non-transitory memory on a computing device (or controller) in imaging system 200. In one embodiment, computing device 216 may include such executable instructions to automatically generate a difference image based on two sequentially acquired images during an early stage of scan acquisition. The difference image may be used to determine whether motion is occurring near but outside of the ROI, which determination may be used to coordinate the start of scan acquisition between an automated and an assisted mode in accordance with the executable instructions.
[0031] By allowing the CT system to operate in either an automatic or assisted mode at the start of a diagnostic scan, the start of scan acquisition may correspond more closely to the appearance of contrast in the ROI, thereby improving the quality of the reconstructed image output by the CT system. In the automatic mode, the scan acquisition may be initiated without operator input, while in the assisted mode, the scan acquisition may be initiated with input from the operator or a machine learning model. For example, during CT imaging of a subject, the subject may move while the CT system is operating. In some examples, such as when a contrast agent is used to improve resolution, the CT system may be configured to automatically initiate scan acquisition upon detection of a threshold increase in contrast (e.g., image contrast) in an acquired image of the ROI compared to a previously acquired image. However, when subject motion occurs, distortion of the acquired image may falsely trigger a diagnostic scan acquisition. In some examples, inaccurate detection of the increase in contrast may occur as a result of image noise.
[0032] As a result, the reconstructed image may have poor image quality, e.g., resolution and sharpness, due to imprecise triggering of scan acquisition, requiring further scanning of the subject. Furthermore, an operator may be discouraged from using automated modes of initiating scan acquisition, since such modes tend to be triggered by events other than the reaching of a threshold contrast increase. As a result, an operator may rely entirely on manual triggering of scan acquisition, which may reduce workflow efficiency and increase operator burden.
[0033] In one embodiment, as described herein, the above-mentioned problems may be at least partially addressed by adapting the CT system to an assisted mode for initiating scan acquisition that may operate in conjunction with the automated mode. The assisted mode may include instructions to generate at least one difference image during initial frame acquisition and evaluation, such as after a scout image has been acquired and before contrast agent is predicted to reach the ROI. The difference image may be generated from the actual current image and the initial mask image and may be displayed to the operator on a display screen of the operator console, such as the display 232 of FIG. 2, so that the operator can override operation in the automated mode and instead select operation in the assisted mode of scan acquisition based on observation of the difference image. Also, an actual image of the ROI, such as a cross-sectional image acquired by the CT system, may be projected on the display screen, which additionally or alternatively allows the operator to monitor the movement of the actual image.
[0034] In another example, an automated process may be used to evaluate the difference image for motion that may cause distortions that may lead to false triggering of a scan acquisition. If motion is determined to be present, the operator may be notified and presented with the option to switch to an assisted mode of scan acquisition, where the operator may manually trigger a scan acquisition. Concurrently with processing of the difference image by the image processing algorithm, the operator may also view the difference image on a display screen and manually select operation in the assisted mode based on visual inspection of the difference image.
[0035] For example, a machine learning algorithm may be used to analyze the difference image to identify motion. If motion is detected, the machine learning algorithm may include instructions to delay initiation of scan acquisition until motion is no longer detected. In this manner, scan acquisition may be initiated via an automated mode assisted by machine learning.
[0036] Additionally, machine learning algorithms may be used to adjust a position of the ROI from frame to frame during frame collection before the start of scan acquisition. For example, a trained machine learning model may be configured to identify an ROI in an image, track the position of the ROI based on the difference image, and output an updated image with the ROI in real time. As an example, the machine learning model may learn based on the acquired data and the data manipulated, e.g., moved, in a known manner to simulate movement of the ROI. For example, supervised learning may be accomplished using a motionless reference image along with multiple simulations of moving objects. The machine learning model may output an indication of whether patient movement has been detected between the reconstructed time frames.
[0037] Alternatively, re-registration of the ROI can be performed using fast image alignment algorithm motion. For example, an initial image, e.g., a mask image, can be used as a template for aligning subsequently acquired images. Image registration algorithms such as rigid registration and deformable registration approaches can be used to achieve image registration, or a registration model can be trained in a similar manner as described above for the machine learning model. When the displayed actual image is updated, the ROI is repositioned in the actual image.
[0038] As another option for tracking the location of the ROI, the entire image, such as a mask image, can be registered prior to placing the ROI. Subsequent acquired images can be registered relative to landmarks, which are easily identifiable features proximate to the ROI. Image registration allows the location of the ROI to be updated for subject motion. Such automated ROI registration can provide accurate measurements of CT numbers despite patient motion. Automated registration can be achieved using a model trained as described above for machine learning models, but the model output can instead be coordinates for translating the ROI, rather than a binary value indicating whether motion has occurred or not. Alternatively, in examples where fast image alignment is utilized, no translation of the ROI is required, but translation of the ROI is required when fast image alignment is applied. In either example, the user can view the image, and the ROI can be robustly positioned on the anatomy of interest, such as the aorta. However, image registration is a relatively slow process and may not be applicable when motion causes the ROI to move out of the imaging plane.
[0039] Details of assisted scan acquisition initiation are provided below in the description of Figures 3-11. Turning first to Figure 3, an example of a scout image 300 is shown. The scout image 300 may be acquired by a CT system at the start of an imaging event and used to indicate the target area to be imaged. For example, the scout image 300 may be a digital radiograph, e.g., a two-dimensional x-ray image, including an anatomical region of a subject, from which cross-sectional images may be acquired. The scan range of a subsequent CT scan acquisition may be defined by the scout image 300.
[0040] A marker may be placed on the scout image 300 to indicate a desired scan plane for a CT scan acquisition. For example, an operator may add a line 302 directly to the scout image 300, which may then be used to position a gantry of a CT system, such as the gantry 102 of FIGS. 1 and 2, to target the indicated scan plane. Cross-sectional images may then be acquired according to the line 302. An example of a first cross-sectional image 400 corresponding to the line 302 of the scout image 300 is depicted in FIG.
[0041] The first cross-sectional image 400 is a frame showing a slice of the subject's anatomy and may be acquired while the CT system gantry is stationary. A marker indicating an ROI 402 may be placed on the first cross-sectional image 400, for example by an operator, to indicate a particular location where data collection is desired. The ROI 402 may be, by way of example, an aorta that may be adjacent to landmarks 404 that are other anatomical features, such as bones.
[0042] If automated scan acquisition initiation is implemented, the ROI 402 can be monitored for changes in visual parameters, for example, a contrast agent can be introduced, e.g., injected or ingested, into the subject, and frames acquired subsequent to the first cross-sectional image 400 (with the gantry also remaining stationary) can be monitored for changes in contrast in the ROI as the contrast agent circulates within the subject.
[0043] As an example, a second cross-sectional image 500 is depicted in Figure 5 capturing the same field of view (FOV) as the first cross-sectional image 400, including the ROI 402 and the landmarks 404. The second cross-sectional image 500 may be a frame acquired immediately after the first cross-sectional image 400 is acquired according to a predetermined image acquisition frequency. Alternatively, the second cross-sectional image 500 may be a frame acquired after the first cross-sectional image 400, but not immediately thereafter (e.g., additional frames have been acquired in the meantime).
[0044] In the second cross-sectional image 500, contrast may increase in the ROI 402 due to infiltration of the contrast agent. The change in contrast may affect the attenuation of x-rays, and a change in contrast may be observed in the scan when the contrast agent reaches the ROI 402. The scan may be processed using image processing algorithms, and acquisition of a diagnostic scan may be automatically initiated when the change in contrast in the ROI 402 in a frame reaches a preset threshold.
[0045] However, the automated mode of scan acquisition initiation may not be robust to motion that causes contrast in the ROI to appear to change, resulting in false triggering of scan acquisition. For example, if the subject moves during the initial period of image acquisition to monitor contrast changes between images, adjacent anatomical features may move into the marked ROI. As an example, landmark 404 may move into the area marked as ROI 402 by the operator as the subject moves. The difference in bone-to-aorta contrast may be sufficient to trigger the contrast change to reach a threshold and trigger acquisition of a diagnostic scan.
[0046] Motion around and outside the ROI can be detected from a difference image generated from the acquired cross-sectional images. The difference image may be an image resulting from the subtraction of one image frame from another image frame, where the frames are acquired at different times. If no motion occurs outside the ROI 402, a first difference image 600 depicted in FIG. 6 may be generated.
[0047] In one example, the first difference image 600 may be generated by subtracting a first cross-sectional image acquired before the contrast agent is delivered to the subject from a second cross-sectional image acquired after the contrast agent is delivered to the subject. The first cross-sectional image may be referred to as a mask image, and the second cross-sectional image may be referred to as a contrast image. The mask image may be subtracted from the contrast image pixel by pixel to generate the first difference image 600, which may be displayed to the operator in real time. The ROI 402 in the first difference image 600 is a distinct circular spot that exhibits high contrast relative to the area surrounding the ROI 402. However, it will be appreciated that variations in the appearance of the ROI in the difference image may vary depending on the type of anatomical feature targeted in the ROI.
[0048] However, if motion occurs in and / or around the ROI 402, a difference image can be generated instead, such as the second difference image 700 shown in FIG. 7. The second difference image 700 can be generated, for example, by subtracting the first cross-sectional image (e.g., mask image) from the second cross-sectional image (e.g., contrast image) acquired later, as described above. In the second difference image 700, the ROI 402 also appears as a bright circular spot with high contrast relative to the surrounding area. Additional structures are also visible in the difference image 700, which may appear as distortions 702. The distortions 702 may result from misregistration of anatomical features captured in the first and second cross-sectional images, which is a result of movement in and / or around the ROI 402.
[0049] In one embodiment, when the second difference image 700 is displayed to the operator, the operator may observe the distortion 702 and choose to override automated scan acquisition initiation in the CT system to mitigate false triggering of a diagnostic scan acquisition. As another example, the difference image generated in real time during the initial monitoring period of a CT scan acquisition event may be processed with an image processing algorithm (e.g., software) to detect motion by identifying distortions such as the distortion 702 in FIG. 7. Upon identifying a distortion from the difference image, the image processing algorithm may include instructions to display a notification to the operator that motion has been detected. The operator may then decide how to proceed, for example, by continuing with automated scan acquisition initiation or by switching to manual, operator-activated initiation.
[0050] Additionally or alternatively, the machine learning algorithm of the machine learning model may be trained to detect motion within the ROI based on the difference image. For example, the machine learning algorithm may be trained to analyze the difference image for the presence of distortion using various techniques such as feature mapping, image registration, image classification, etc. Furthermore, the machine learning algorithm may be trained by simulating patient motion by resampling the volume between subsequent time frames. Upon detection of distortion, the machine learning algorithm may be configured to notify an operator of the detected motion, as described above with reference to processing via the image processing algorithm, by way of example. This allows the operator to decide whether to proceed with an automated or assisted (e.g., manual) scan acquisition initiation.
[0051] As another example, the trained machine learning model may be integrated into an automatic mode of scan acquisition initiation. For example, the difference image may be automatically monitored and analyzed by the machine learning model to detect motion within the ROI based on distortion identification. Upon detecting motion within the ROI, the trained machine learning model may override the automatic mode of scan acquisition initiation (e.g., a default setting of the automatic mode used when no motion is detected).
[0052] The machine learning model may be further configured to generate a vector map based on the difference image, which may be used to guide repositioning of the ROI to reflect the actual location of the target anatomical feature being scanned. The contrast image and / or the difference image may be updated with the repositioned ROI with every newly acquired image frame to monitor the contrast. When the contrast reaches a threshold, scan acquisition may be initiated.
[0053] The machine learning model may be implemented in a machine learning assisted automatic mode, but an option may be provided for the operator to override the machine learning assisted automatic mode and switch to manually initiated scan acquisition. If the operator chooses to manually initiate scan acquisition, the machine learning model may continue to reposition and update the ROI in the contrast and / or difference images.
[0054] Alternatively, the ROI may be repositioned based on a fast image alignment algorithm or image registration, as described above. If a fast image alignment algorithm is used, the contrast and / or difference images may be displayed with the repositioned ROI as the images are updated. For image registration, the contrast cross-sectional image acquired in real time may be registered to the mask cross-sectional image acquired at the start of the scan acquisition event. If motion is detected near or around the ROI, for example by an operator or a machine learning model, the motion may be used to reposition the ROI.
[0055] For example, the images can be registered based on landmarks identified in the mask and contrast images as described above. For example, the location of the ROI 402 in the mask image relative to the landmarks 404 of Figures 4 and 5 representing bones can be determined. The landmarks 404 are more opaque and their contrast may not depend on the contrast agent. The change in the location of the landmarks may be mapped and used to reposition the ROI depending on its relative location to the landmarks.
[0056] Image registration can provide an established method for image re-registration that is widely used for 2D image registration. However, for CT systems, ROI motion can occur within the imaging plane or out of the imaging plane depending on how the subject moves. Thus, image registration can be reliable for motion compensation within the imaging plane, but may not be able to track motion in directions other than along the imaging plane. Similarly, fast image registration algorithms may only be an efficient technique for 2D image registration. Furthermore, image registration can be an iterative, computationally intensive process, requiring a completion time longer than the frequency of frame capture. Thus, ROI re-registration using machine learning models may be more efficient and more robust.
[0057] A high level workflow 800 of a CT system configured with automated and assisted modes of scan acquisition initiation is shown in FIG. 8. As an example, the CT system may be the imaging system 200 of FIG. 2. At 802 of the workflow 800, a threshold increase in contrast is set as a trigger for initiating scan acquisition, which may depend on the kVp of the acquisition and the contrast injection protocol used. The threshold may be set before a scout image is acquired or after the scout image is acquired but before cross-sectional image acquisition is initiated (e.g., a cross-sectional image used as a trigger for diagnostic scan acquisition). After the threshold is set, cross-sectional image acquisition may be initiated, which may include acquiring a mask image followed by a contrast image. The operator may specify an ROI in the mask image, which is propagated to the subsequently captured contrast images.
[0058] A difference image may be generated from the mask image, and the contrast in the ROI may be determined from the difference image. The difference image may be updated at a rate corresponding to the image acquisition frequency of the contrast image. At 804 of the workflow 800, the difference image may be used to detect motion outside the ROI and within the frame of the difference image according to any of the strategies described above. If no motion is detected, the workflow 800 proceeds to 806 to initiate diagnostic scan acquisition via an automated mode that does not depend on operator input. For example, a scan acquisition may be triggered when it is determined that the contrast of the difference image reaches a threshold value.
[0059] However, if motion is detected at 804, the workflow 800 instead proceeds to 808 and switches to assisted mode to initiate diagnostic scan acquisition. In some embodiments, rather than automatically switching to assisted mode in response to motion detection, a prompt for input from the operator may be displayed, providing an alert that motion has been detected and presenting an option to switch to assisted mode. Assisted mode may rely on the operator initiating scan acquisition or may rely on machine learning models. In one embodiment, when operator assisted, an option may be provided to reposition the ROI, either by fast image alignment or machine learning models, to allow the operator to better identify when to trigger scan acquisition. When assisted by machine learning models, the ROI may be repositioned and monitored for contrast changes.
[0060] The algorithms providing instructions for performing assisted and automatic scan acquisition initiation in the CT system may include commands to output and display information to an operator, for example, on a display screen. The displayed information may include a real-time graph 900 plotting contrast in an ROI in a difference image over time, as shown in FIG. 9, where the contrast in the difference image is representative of the change in contrast between the images used to generate the difference image. Each of the multiple data points 902 may be generated as the difference image is updated based on the acquisition of a new contrast image, where the difference image takes into account movement as the ROI is repositioned between image frames. The contrast images may be collected according to a preset frequency, and the real-time graph 900 may be updated with new data points at a rate corresponding to the preset frequency.
[0061] The real-time graph 900 may include a threshold contrast 904, as indicated by the dashed line. The threshold contrast 904 may be an increase in contrast that indicates that contrast agent has reached the ROI. The real-time graph 900 may be displayed at least during the early stages of a CT imaging event, such as before a diagnostic scan acquisition is triggered.
[0062] The display of the real-time graph 900 may also provide the operator with a visual count down of the period during which override of the automatic scan acquisition initiation is permitted. For example, during the period indicated by brackets 906, the operator may be presented with the option to switch to an assisted mode of scan acquisition initiation if motion is detected (by the operator or by a machine learning model). This period may extend from after the first cross-sectional image, which may be used as a mask image, is acquired, until the contrast reaches the threshold contrast 904. If a switch to assisted mode is not indicated before the timer period expires, acquisition of the diagnostic scan may proceed once the contrast reaches the threshold contrast 904.
[0063] If the operator chooses to switch to assisted mode within the period indicated by bracket 906, the display of real-time graph 900 may be maintained and the display of images, as described below with reference to Figure 10, may be continually updated as new images are acquired and generated. However, after the period indicated by bracket 906, the option to switch to assisted mode may no longer be available and graph 900 may be removed from the display.
[0064] As shown in FIG. 10 in one example of a display screen 1000, the real-time graph 900 may be displayed along with a cross-sectional image, which may be the first cross-sectional image 400 of FIG. 4, or in other examples the second cross-sectional image 500 of FIG. 5, or any mask or contrast image recently captured early in a CT imaging event.
[0065] The display screen 1000 may also display a difference image, which may be, by way of example, the second difference image 700 of Figure 7. The displayed difference image may be the most recently generated difference image, and may be updated as new contrast-enhanced images are acquired. The cross-sectional and difference images may be presented early in the CT imaging event, allowing the operator to observe changes in contrast and sharpness in the cross-sectional images and the presence of distortions in the difference image.
[0066] For example, the cross-sectional image 400 is displayed and updated each time a new cross-sectional image is acquired. Each refresh of the cross-sectional image may correspond to one of the data points 902 of the real-time graph 900 that is added as the cross-sectional images are acquired. The difference image may be displayed after the first cross-sectional image, which may be a mask image, is acquired, as shown by bracket 906 in FIG. 9. In some embodiments, movement around the image ROI may be visible in the cross-sectional image and may be used by the operator to determine whether the assisted mode is desired. A manual activation request for switching to the assisted mode, such as, for example, a selectable button, may be included in the display screen 1000.
[0067] The time period indicated by bracket 906 in FIG. 9 allows the operator to monitor the difference image, which is updated as each new cross-sectional image is acquired and used to generate the difference image. In one embodiment, if distortion is present in the difference image, it may be easily observed by the operator and may additionally trigger the display of a notification regarding motion detected outside the image ROI. The notification indication may be output by the image processing software. Additionally, an option to switch to an assisted mode of initiating scan acquisition may be presented.
[0068] If the operator selects the assisted mode, the operator can monitor the difference image and initiate scan acquisition based on visual observation. For example, the operator can manually trigger scan acquisition when he observes that the distortion is no longer present in the difference image. If the distortion persists through the period indicated by bracket 906 in FIG. 9, the operator can abort scan acquisition or allow scan acquisition to begin when data point 902 of graph 900 reaches threshold contrast 904.
[0069] Alternatively, the machine learning model can be used to monitor the difference image for distortion from the start of the acquisition of the cross-sectional image. If distortion indicative of motion outside the ROI is detected, the machine learning model can automatically override the automatic scan acquisition start to control the triggering of the scan acquisition. The scan acquisition can be triggered by the machine learning model when motion is no longer detected in the difference image. The machine learning model can also include instructions to monitor the contrast according to the data points 902 of the graph 900. If a period of time has passed as shown in the bracket 906 of FIG. 9 and motion is still detected outside the ROI, the operator can be presented with the option to, for example, stop the scan acquisition or continue the scan acquisition. The graph 900 can be displayed until the contrast reaches a threshold contrast 904 or until no motion is detected in the difference image and the scan acquisition is started. Similarly, the difference image can be removed from the display screen 1000 once the scan acquisition is started.
[0070] In this way, the use of automatic scan acquisition initiation in CT systems may be more robust to motion occurring outside of the ROI that may otherwise lead to false triggering of scan acquisition. By implementing an assisted mode that may be used to override the automatic mode when motion is detected, scan acquisition may be triggered at the discretion of the operator or following analysis by a machine learning model. Motion may be identified from a difference image that is generated by subtracting a mask image from a contrast image that is continuously acquired and updated until a contrast change in the image reaches a threshold. By configuring an assisted mode (e.g., by a machine learning model or an operator) as an option to support the automated mode, the use of the automated mode may become more attractive to the operator. The overall work flow and efficiency may be improved while the subject's x-ray exposure may be reduced.
[0071] An example of a method 1100 for acquiring diagnostic CT scans is depicted in Figures 11A-11B. Instructions for performing the method 1100 may be executed by a processor of a computing device, such as computing device 216 of Figure 2, based on instructions stored in a memory of a controller. In one embodiment, the CT system may be CT system 100 or imaging system 200 of Figure 2. The instructions may include algorithms for fast image registration and / or machine learning models trained to analyze images acquired and generated by the CT system. The CT system may be configured to operate in an automatic mode, in which contrast in the difference images may be automatically monitored, a manual mode, in which image and scan acquisition is controlled by an operator, and an assisted mode, which may be performed in conjunction with the automatic mode.
[0072] Prior to or at the start of the method 1100, a contrast agent may be delivered to the subject being scanned. For example, the contrast agent may be injected into or ingested by the subject. An estimated duration for the contrast agent to circulate in the subject and reach a target region of the subject may be predetermined and used as a time frame criterion for the execution of the method 1100. For example, the method 1100 may be performed within the duration between the delivery of the contrast agent to the subject and the circulation of the contrast agent to the target region such that an enhanced contrast may be observed. In this manner, certain elements such as difference images and graphs as further described below may be generated and displayed only before the contrast agent reaches the ROI.
[0073] Turning first to FIGURE 11A, at 1102, method 1100 includes determining whether an automated mode of operation has been selected by an operator. If the automated mode has not been selected, method 1100 proceeds to 1104 to operate in a manual mode. In the manual mode, an operator may view cross-sectional images acquired by the CT system and displayed on a display device, such as display device 232 of FIGURE 2. The operator may manually initiate acquisition of a diagnostic scan if motion between time frames is apparent based on viewing the difference images.
[0074] If an automated mode is selected, for example by an operator, method 1100 proceeds to 1106 to acquire a scout image. For example, the scout image may be scout image 300 of FIG. 3 and is used to orient the CT system with respect to the subject and to indicate from where the cross-sectional images will be acquired. After the scout image is acquired, a mask image is acquired at 1108. The mask image may be the first cross-sectional image acquired of the area indicated in the scout image with the CT system gantry stationary.
[0075] At 1110, the method 1100 includes determining whether an ROI has been indicated. For example, the ROI may be indicated by an operator selecting or placing a marker on the mask image. If an ROI has not been indicated, the method 1100 is held at 1110 until an ROI is indicated. If an ROI has been indicated by the operator, the method 1100 proceeds to 1112 to acquire a contrast image and generate a difference image based on the contrast image and the mask image. The contrast image and difference image may be displayed to the operator along with a graph plotting contrast at the ROI in the difference image over time, such as graph 900 in FIGS. 9 and 10. The difference image may be generated by subtracting the mask image pixel by pixel from the contrast image, resulting in an image such as the example difference images depicted in FIGS. 6-7.
[0076] At 1114, the method 1100 includes determining whether motion is detected in the difference image outside the ROI. For example, motion in the subject may be indicated by the presence of distortions in the difference image, such as distortion 702 in FIG. 7. The distortions may be identified by an operator based on visual observation or by a machine learning model. If motion is not detected, the method 1100 continues at 1116 to determine whether the contrast at the ROI in the difference image reaches a threshold contrast. The threshold contrast may correspond to an expected change in contrast when contrast agent reaches the ROI.
[0077] If the contrast does not meet the threshold, method 1100 returns to 1112 to acquire another contrast image and generate a corresponding difference image. The newly acquired contrast image and corresponding difference image may replace the previous contrast image and difference image, thereby updating the display on the display device. The graph may also be updated to include new data points corresponding to the contrast in the newly generated difference image. If the contrast meets the threshold at 1116, method 1100 proceeds to 1128 (as shown in FIG. 11B) to remove the difference image and graph from the display, as described below.
[0078] Returning to 1114, if motion is detected in the difference image, method 1100 proceeds to 1118 to display a notification or warning to the operator that motion is present. Displaying a notification or warning may also include displaying or prompting the operator with an option to switch to an assisted mode of operation. At 1120, method 1100 includes checking whether assisted mode has been requested. If a request for assisted mode is not confirmed at 1120, method 1100 proceeds to 1116 as described above to check whether the contrast in the difference image reaches a threshold. If a request for assisted mode is confirmed at 1120, method 1100 proceeds to 1122 to continue acquiring contrast images, generating difference images, and updating the display of images and graphs.
[0079] In one example, refreshing the display of the contrast image may include repositioning the ROI every frame to compensate for subject motion. The ROI may be repositioned using, as an example, a fast image registration algorithm. In another example, the mask image may be registered before placing the ROI, and the contrast image may be registered to the mask image instead of repositioning the ROI. In yet another example, the ROI may be repositioned by a machine learning model based on a vector map generated by the machine learning model to predict the movement of the ROI. For example, the vector map may be generated from the difference image, for example, by analyzing distortion. In an implementation, using a machine learning model to update the position of the ROI in the displayed contrast image may be faster and less computing-intensive than image registration.
[0080] Turning now to FIG. 11B, at 1124, the method 1100 includes checking whether the contrast of the ROI in the difference image reaches a threshold, as described above at 1116. If the contrast does not reach the threshold, the method 1100 proceeds to 1126 to check whether a request to initiate a diagnostic scan has been received. If no request is received, the method 1100 returns to 1124 to check again whether the contrast reaches the threshold. If a request to initiate a diagnostic scan has been received at 1126, the method 1100 proceeds to 1128 to stop displaying the difference image and graph. In other words, the difference image is no longer generated and both the difference image and graph may be removed from display on the display device. The option to switch to the assisted mode is no longer available, if not already selected. The method 1100 then proceeds to 1130 to begin acquiring a diagnostic scan of the ROI. A request to initiate a scan acquisition may be received from the operator when the operator observes that distortion is no longer present in the difference image. Alternatively, the request may be received from the machine learning model when the machine learning model determines, based on analysis of the difference image, that motion is no longer present.
[0081] Returning to 1124, if the contrast in the ROI of the difference image reaches a threshold, method 1100 proceeds to 1132 to check whether a request to stop the scan acquisition has been received. For example, an operator may request that the scan acquisition be stopped if motion does not stop and / or if the motion is of a magnitude that impairs the ability to obtain useful information from the diagnostic scan. Similarly, a request to stop the scan acquisition may be received from the machine learning model if the machine learning model determines that motion is too great to reliably track the ROI and that the resulting scan is likely to be unusable. If a request to stop is received at 1132, the scan acquisition event ends at 1134. If a request to stop is not received, method 1100 proceeds to 1128 to remove the difference image and graphs from display on the display screen. Method 1100 proceeds to 1130 to begin acquiring a diagnostic scan.
[0082] FIG. 1 illustrates an example configuration with the relative positional relationships of various components. When shown as being in direct contact or directly coupled to one another, such elements may, at least in one example, be referred to as being in direct contact or directly coupled, respectively. Similarly, elements shown consecutive or adjacent to one another may, at least in one example, be consecutive or adjacent, respectively. As an example, components laid out in surface contact with one another may be referred to as being in surface contact. As another example, in at least one example, elements placed apart from one another with only space between them and no other components may be so referred to. As yet another example, elements shown above / below one another, opposite one another, or to the left / right of one another may be so referred to with respect to one another. Additionally, as shown in the figures, in at least one example, the topmost element or point of an element may be referred to as the "top" of the element, and the bottommost element or point of an element may be referred to as the "bottom" of the element. As used herein, up / down, up / down, and up / down are relative to the vertical axis of the figure and may be used to describe the positional relationships of the elements of the figure with respect to one another. Thus, elements shown above other elements are, in one example, vertically disposed above the other elements. As yet another example, the shapes of elements depicted in the figures may be referred to as having those shapes (e.g., circular, rectilinear, planar, curved, rounded, chamfered, angled, etc.). Additionally, elements shown intersecting one another may, at least in one example, be referred to as intersecting elements or intersecting one another. Additionally, elements shown within or outside of other elements may, by way of example, be so referred to.
[0083] The present disclosure also provides support for a method for an X-ray imaging system, the method including the steps of: generating a difference image from a first image and a second image in response to operation of the X-ray imaging system in an automated mode; and displaying the difference image on a display device to enable detection of movement outside a region of interest (ROI) based on analysis of the difference image, the difference image being displayed before the contrast agent reaches the ROI. In a first embodiment of the method, the difference image is displayed after the second image is acquired and is continuously updated on the display device as new images are acquired. In a second embodiment of the method, optionally including the first embodiment, but once the contrast agent reaches the ROI, the difference image is no longer displayed. In a third embodiment of the method, optionally including one or both of the first and second embodiments, the first image is a mask image, the second image is a contrast image, both the first image and the second image are displayed on the display device, and the difference image is generated by subtracting the first image from the second image. In a fourth embodiment of the method, optionally including one or more of the first to third embodiments, motion outside the ROI is detected by the presence of distortion around the ROI in the difference image. In a fifth embodiment of the method, optionally including one or more of the first to fourth embodiments, the method further includes continuously acquiring new images and displaying the actual image with the new images, where a new difference image is generated with each new image and displayed on the display device. In a sixth embodiment of the method, optionally including one or more of the first to fifth embodiments, the method further includes presenting a notification on the display device if motion is detected outside the ROI, the notification including an option to switch operation of the X-ray imaging system to an assisted mode. In a seventh embodiment of the method, optionally including one or more of the first to sixth embodiments, the method further includes starting scan acquisition based on input from an operator based on visual observation of motion by the operator when the X-ray imaging system operates in an assisted mode.An eighth embodiment of the method optionally includes one or more of the first to seventh embodiments, and wherein motion is detected using a machine learning model trained to identify motion in the difference image or by an operator visually observing the difference image. A ninth embodiment of the method optionally includes one or more of the first to eighth embodiments, and wherein a graph plotting contrast in the ROI of the difference image against time is also displayed on the display device, with each data point on the graph corresponding to the acquisition of a new contrast image and a corresponding generation of a new difference image.
[0084] The present disclosure also provides support for an x-ray imaging system comprising an x-ray source and an x-ray detector disposed on opposite sides of a gantry, a subject disposed within the gantry between the x-ray source and the x-ray detector, and a processor of a computing device configured with executable instructions that, when executed, cause the processor to: generate a difference image by subtracting a mask image from a contrast image when operating in an automatic mode, display the difference image on a display device, display a notification when motion outside the ROI is detected in the difference image, and acquire a diagnostic scan in response to receiving a request to initiate a diagnostic scan acquisition, the request to initiate a diagnostic scan acquisition being received when motion outside the ROI is no longer detected in the difference image. In a first embodiment of the system, the mask image is a first cross-sectional image acquired by the x-ray imaging device, the contrast image is a cross-sectional image acquired after the mask image, and the contrast image is acquired at a predetermined frequency and displayed on the display device along with the difference image. A second embodiment of the system optionally includes the first embodiment, where the display of the difference image and the contrast image are refreshed according to a predetermined frequency until the contrast at the ROI in the difference image reaches a threshold contrast, which indicates that the contrast agent has reached the ROI. A third embodiment of the system optionally includes one or both of the first and second embodiments, where motion in the difference image is automatically detected by a machine learning model trained to detect motion in the difference image based on the presence of distortion. A fourth embodiment of the system optionally includes one or more or each of the first through third embodiments, where the machine learning model is further trained to determine a new position of the ROI based on the difference image and to reposition the ROI in the contrast image when the display of the contrast image on the display device is updated.
[0085] The present disclosure also provides support for a method for operating an X-ray imaging system, comprising: generating a difference image from a mask image and a contrast image in response to operation of the X-ray imaging system in an automatic scan acquisition start mode; displaying the difference image and the contrast image on a display device; providing an option to switch operation of the X-ray imaging system to an assisted scan acquisition start mode if motion is detected in the difference image outside a region of interest (ROI); continually refreshing the display of the difference image and the contrast image upon receiving confirmation to switch operation to the assisted scan acquisition start mode, where refreshing the display includes repositioning the ROI to compensate for the motion; and initiating diagnostic scan acquisition in response to receiving a request to start diagnostic scan acquisition. In a first embodiment of the method, the method further includes aborting diagnostic scan acquisition if an abort request is received from an operator or a machine learning model. In a second embodiment of the method, optionally including the first embodiment, repositioning the ROI includes updating the contrast image with a new position between frames of the ROI using a fast image registration algorithm. In a third embodiment of the method, optionally including one or both of the first and second embodiments, the position of the ROI is tracked in the contrast image based on image registration, the image registration being performed before the ROI is indicated in the contrast image.In a fourth embodiment of the method, optionally including one or more or each of the first to third embodiments, repositioning the ROI includes updating the position of the ROI in the contrast image on a frame-by-frame basis by a machine learning model, the machine learning model being configured to generate a vector map based on the difference image to determine the position of the ROI.
[0086] As used herein, an element or step described in the singular and preceded by the word "a" or "an" should be understood not to exclude a plural of that element or step, unless such exclusion is expressly stated. Moreover, reference to "one embodiment" of the invention is not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features. Furthermore, unless expressly stated to the contrary, an embodiment that "includes," "has," or "has" an element or elements having a particular characteristic may include additional such elements that do not have that characteristic. The terms "including" and "having" are used as plain-language equivalents of the respective terms "including" and "having." Furthermore, terms such as "first," "second," and "third" are merely used as labels and are not intended to impose numerical requirements or a particular positional order on their objects.
[0087] Examples are used herein to disclose the invention, including the best mode, and also to enable any person of ordinary skill in the art to practice the invention, including making and using any devices or systems, and performing the incorporated methods. The patentable scope of the invention is defined by the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements that do not differ substantially from the literal language of the claims.
[0088] Further aspects of the invention are provided by the subject matter of the following clauses. [Embodiment 1] 1. A method for an x-ray imaging system, comprising: Responding to operation of the x-ray imaging system in an automatic mode; generating a difference image from the first image and the second image; displaying the difference image on a display device and enabling detection of motion outside the region of interest (ROI) based on analysis of the difference image; wherein the difference image is displayed before the contrast agent reaches the ROI. [Embodiment 2] 2. The method of embodiment 1, wherein the difference image is displayed after the second image is acquired and is continually updated on the display device as new images are acquired. [Embodiment 3] 2. The method of embodiment 1, wherein when the contrast agent reaches the ROI, the difference image is no longer displayed. [Embodiment 4] 2. The method of claim 1, wherein the first image is a mask image and the second image is a contrast image, both the first image and the second image are displayed on a display device, and the difference image is generated by subtracting the first image from the second image. [Embodiment 5] 2. The method of claim 1, wherein movement outside the ROI is detected by the presence of distortion around the ROI in the difference image. [Embodiment 6] The method of embodiment 1 further includes the steps of continuously acquiring new images and displaying the actual image with the new images, each of which generates a new difference image and displays it on the display device. [Embodiment 7] The method of embodiment 1, further comprising the step of presenting a notification on a display device when movement is detected outside the ROI, the notification including an option to switch operation of the X-ray imaging system to an assisted mode. [Embodiment 8] 8. The method of embodiment 7, wherein when the X-ray imaging system operates in an assisted mode, scan acquisition is initiated based on input from an operator based on visual observation of movements by the operator. [Embodiment 9] The method of embodiment 1, wherein the movement is detected using a machine learning model trained to identify movement in the difference image or by an operator visually observing the difference image. [Embodiment 10] The method of embodiment 1, wherein a graph plotting contrast at the ROI in the difference image against time is also displayed on the display device, with each data point on the graph corresponding to the acquisition of a new contrast image and the generation of a corresponding new difference image. [Embodiment 11] 1. An x-ray imaging system comprising: an X-ray source and an X-ray detector disposed on opposite sides of the gantry; a subject disposed in a gantry between an x-ray source and an x-ray detector; A processor of a computing device configured with executable instructions that, when executed, cause the processor to: When operating in an automatic mode, subtracting the mask image from the contrast image to generate a difference image; displaying the difference image on a display device; displaying a notification if motion outside the ROI is detected in the difference image; acquiring a diagnostic scan in response to receiving a request to initiate a diagnostic scan acquisition; and a processor for executing the An x-ray imaging system, wherein a request to start acquiring a diagnostic scan is received when motion outside the ROI is no longer detected in the difference image. [Embodiment 12] An X-ray imaging system as described in embodiment 11, wherein the mask image is a first cross-sectional image acquired by an X-ray imaging device, the contrast image is a cross-sectional image acquired after the mask image, and the contrast image is acquired at a predetermined frequency and displayed on a display device together with the difference image. [Embodiment 13] An X-ray imaging system as described in embodiment 12, wherein the display of the difference image and the contrast image is refreshed according to a predetermined frequency until the contrast of the ROI in the difference image reaches a threshold contrast, which indicates that the contrast agent has reached the ROI. [Embodiment 14] An X-ray imaging system as described in embodiment 11, wherein motion is automatically detected in the difference image by a machine learning model trained to detect motion in the difference image based on the presence of distortion. [Embodiment 15] An X-ray imaging system as described in embodiment 14, wherein the machine learning model is further trained to determine a new position of the ROI based on the difference image and to reposition the ROI within the contrast image when the display of the contrast image on the display device is updated. [Embodiment 16] 1. A method of operating an x-ray imaging system, comprising: generating a difference image from the mask image and the contrast image in response to operation of the radiography system in an automatic scan acquisition initiation mode, and displaying the difference image and the contrast image on a display device; providing an option to switch operation of the x-ray imaging system to an assisted scan acquisition initiation mode if motion is detected in the difference image outside a region of interest (ROI); upon receiving confirmation to switch operation to an assisted scan acquisition initiation mode, continually updating a display of the difference image and the contrast image, where updating the display includes repositioning the ROI to compensate for motion; initiating a diagnostic scan acquisition in response to receiving a request to initiate a diagnostic scan acquisition. [Embodiment 17] 17. The method of embodiment 16, further comprising the step of stopping the diagnostic scan acquisition if a stop request is received from an operator or the machine learning model. [Embodiment 18] 17. The method of embodiment 16, wherein repositioning the ROI includes updating the contrast image with the new frame-to-frame position of the ROI using a fast image registration algorithm. [Embodiment 19] 17. The method of embodiment 16, wherein the position of the ROI is tracked in the contrast image based on image registration, and image registration is performed before the ROI is indicated in the contrast image. [Embodiment 20] The method of embodiment 16, wherein repositioning the ROI includes updating the position of the ROI in the contrast image frame by frame using a machine learning model, the machine learning model being configured to generate a vector map based on the difference image to determine the position of the ROI. [Explanation of symbols]
[0089] 100: CT system 102: Gantry 104: X-ray source 106: X-ray radiation beam 108: Detector array 110: Image processing unit 112, 204: Subject 114: Table 200: Imaging system 202: Detector elements 206: Center of rotation 208: Control mechanism 210: X-ray controller 212: Gantry motor controller 214: DAS 216: Computing device 218: Mass storage device 220: Operator console 224: PACS 226: Table motor controller 230: Image reconstructor 232: Display 300: Scout image 302: Line 400: First cross-sectional image 402: ROI 404: Landmark 500: Second cross-sectional image 600: First difference image 700: Second difference image 702: Distortion 900: Real-time graph 902: Data points 904: Threshold contrast 906: Real-time graph 1000: Display screen
Claims
1. A method for an X-ray imaging system (100), comprising: Responding to operation of the x-ray imaging system in an automatic mode; generating a difference image (600) from the first image (400) and the second image (500); displaying (1114) the difference image (600) on the display device (232) to enable detection of motion outside the region of interest (ROI) (402) based on analysis of the difference image; and the difference image is displayed before the contrast agent reaches the ROI (1122).
2. The method of claim 1 , wherein the difference image (600) is displayed after the second image is acquired and is continually updated (1112) on the display device (232) as new images are acquired.
3. 10. The method of claim 1, wherein once the contrast agent reaches the ROI, the difference image is no longer displayed.
4. 2. The method of claim 1, wherein the first image is a mask image (400) and the second image is a contrast image (500), both the first image and the second image are displayed on a display device (232), and the difference image (600) is generated by subtracting the first image from the second image.
5. The method of claim 1 , wherein motion outside the ROI (402) is detected by the presence of a distortion (702) around the ROI in the difference image (600).
6. 2. The method of claim 1, further comprising the steps of continually acquiring new images and displaying the actual image with the new images, each new image producing a new difference image to be displayed on the display device (232).
7. 2. The method of claim 1, further comprising the step of presenting (1118) a notification on a display device (232) when motion is detected outside the ROI (402), the notification including an option to switch operation of the X-ray imaging system (100) to an assisted mode.
8. The method of claim 7, wherein when the X-ray imaging system (100) operates in an assisted mode, scan acquisition is initiated based on input from an operator based on visual observation of movements by the operator.
9. The method of claim 1 , wherein the motion is detected using a machine learning model trained to identify motion in the difference image (600) or by an operator visually observing the difference image (600).
10. 2. The method of claim 1, wherein a graph (900) plotting contrast at the ROI (402) in the difference image (600) against time is also displayed on the display device (232), with each data point on the graph corresponding to the acquisition of a new contrast image and the generation of a corresponding new difference image.
11. 1. An X-ray imaging system (100), comprising: an X-ray source (104) and an X-ray detector (108) disposed on opposite sides of the gantry (102); a subject (204) disposed in a gantry between an x-ray source and an x-ray detector; A processor of a computing device (216) configured with executable instructions that, when executed, cause the processor to: When operating in an automatic mode, subtracting (1112) the mask image (500) from the contrast image (400) to generate a difference image (600); displaying (1112) the difference image on a display device; displaying (1118) a notification if motion outside the ROI (402) is detected in the difference image; acquiring a diagnostic scan in response to receiving a request to initiate a diagnostic scan acquisition (1130); and a processor for executing the An x-ray imaging system, wherein a request to begin acquiring a diagnostic scan is received when motion outside the ROI is no longer detected in the difference image.
12. 12. The X-ray imaging system (100) of claim 11, wherein the mask image is a first cross-sectional image (400) acquired by the X-ray imaging device, the contrast image (500) is a cross-sectional image acquired after the mask image, and the contrast image is acquired at a predetermined frequency and displayed on a display device together with the difference image.
13. 13. The X-ray imaging system of claim 12, wherein the display of the difference image and the contrast image is refreshed according to a predetermined frequency until the contrast of the ROI in the difference image reaches a threshold contrast, which indicates that contrast agent has reached the ROI.
14. The X-ray imaging system (100) of claim 11, wherein motion is automatically detected in the difference images by a machine learning model trained to detect motion in the difference images based on the presence of distortion.
15. 15. The X-ray imaging system (100) of claim 14, wherein the machine learning model is further trained to determine a new position of the ROI (402) based on the difference image (600) and to reposition the ROI within the contrast image (500) when the display of the contrast image (500) on the display device (232) is updated.
Citation Information
Patent Citations
X-ray computed tomographic system
JP1995194588A
Presence management system
JP2005196330A
Image diagnosis apparatus, image processing method, image processing apparatus and storage medium
JP2005198330A
X-ray CT apparatus and image display method
JP2013169392A
X-ray CT apparatus and imaging method
JP2015150208A
