System and method for x-ray device monitoring using air calibration

Abstract

A non-transitory computer readable medium (26) stores instructions executable by at least one electronic processor (20) to perform a method (100) of monitoring an X-ray imaging device (1). The method comprises: retrieving air calibration data (32) generated by at least one air calibration performed for the X-ray imaging device; deriving a diagnostic metric indicative of a problem or status of the X-ray imaging device from the retrieved air calibration data; and outputting an alarm or status indicator (30) indicative of a problem or status of the X-ray imaging device based on the derived diagnostic metric.

Description

Technical Field

[0001] Generally speaking, the following relates to medical imaging technology, X-ray imaging technology, X-ray calibration technology, X-ray maintenance technology and related technologies. Background Art

[0002] For predictive maintenance of a medical imaging system, sensitive components need to be monitored so that they can be replaced in a timely manner without unplanned downtime. To this end, sensor-based monitoring can be implemented to provide early detection of X-ray tube failures. Generally, a tube add-on equipped with sensors for monitoring is used.

[0003] Current systems can use an auxiliary unit coupled to the tube housing. The auxiliary unit carries tube data from, for example, a tube control unit and additional sensors. Estimation of the remaining tube life is achieved by a model in a remote computer that operates on the data transmitted by the auxiliary unit (prediction can also be done online in the auxiliary unit). For tube anode bearing fault prediction, current systems can also include a diagnostic circuit as a sensor for increasing the anode motor load. An accelerometer is used to measure the acceleration of the gantry and the anode rotation frequency, and acoustic, voltage, and current sensors are used to monitor the anode drive motor.

[0004] In addition, for predicting tube bearing failures, accelerometers, microphones, and vibration sensors have been proposed, such as circuit board devices that detect vibrations in the tube housing during a drop in the inertia of the anode rotor to zero. In addition, combined sensors can be used to detect acoustic noise and vibrations for tube bearing failures. Other systems can use sensors for position, vibration, angle, and temperature measurements of X-ray tube predictive fault indicators. The tube vibration data is converted, and a notification is sent whenever a certain number of diagnostic frequencies are detected.

[0005] Other components besides the X-ray tube can similarly benefit from early detection of indications of component failures. An X-ray detector array is typically constructed as a two-dimensional (2D) array of individual X-ray detectors. Early detection of a decline in the performance of the X-ray detector enables timely replacement without unplanned downtime. In the case of a computed tomography (CT) imaging scanner, a rotating gantry carries an X-ray tube and an X-ray detector array. The gantry is a complex mechanical system that may experience deterioration, such as bearing wear, which may introduce wobbling or other rotational defects that can adversely affect image quality and gantry safety. Similarly, early detection of gantry problems may be beneficial. However, adding sensors to monitor these additional components adds further complexity to the X-ray imaging device, increases costs, and the additional components are prone to failure.

[0006] Certain improvements that overcome these and other problems are disclosed below. Summary of the Invention

[0007] In some embodiments disclosed herein, a non - transitory computer - readable medium stores instructions executable by at least one electronic processor to perform a method of monitoring an X - ray imaging device. The method includes: retrieving air - calibration data generated by at least one air calibration performed on the X - ray imaging device; deriving a diagnostic metric indicative of a problem or a state of the X - ray imaging device based on the retrieved air - calibration data; and outputting an alert or a status indicator indicative of the problem or the state of the X - ray imaging device based on the derived diagnostic metric.

[0008] In some embodiments disclosed herein, an X - ray imaging system includes an X - ray imaging device and a controller configured to control the X - ray imaging device to acquire an air calibration; use the air calibration to determine a gain normalization factor for an X - ray detector of the X - ray imaging device; control the X - ray imaging device to acquire an image of an associated object using the determined gain normalization factor; and store the air - calibration data generated by at least one air calibration. An electronic processor is programmed to retrieve the stored air - calibration data; derive a diagnostic metric indicative of a problem or a state of the X - ray imaging device based on the retrieved air - calibration data; and output an alert indicative of the problem or the state of the X - ray imaging device based on the derived diagnostic metric.

[0009] In some embodiments disclosed herein, a non - transitory computer - readable medium stores instructions executable by at least one electronic processor to perform a method of monitoring an X - ray device. The method includes: retrieving air - calibration data generated by at least one air calibration performed on the X - ray device; deriving a diagnostic metric indicative of a problem or a state of the X - ray device based on the retrieved air - calibration data; and outputting an alert indicative of the problem or the state of the X - ray device based on the derived diagnostic metric.

[0010] One advantage is that air - calibration data is used instead of additional sensors on the X - ray device to monitor the X - ray device.

[0011] Another advantage is that calibration data is used to monitor faults in the X - ray tube, detector, high - voltage generator, high - voltage wiring, bow - tie filter, collimator, and / or gantry.

[0012] Another advantage is that the failure time of the X - ray device is predicted to determine the optimal service time of the X - ray device, thereby reducing the downtime of the X - ray device.

[0013] Another advantage is that X - ray examinations with reduced latency or eliminated are achieved.

[0014] Another advantage lies in reducing the financial losses of a medical institution based on accurately determining the predicted failure date of an X-ray device.

[0015] Another advantage lies in recommending the date of the next air calibration process, reducing the time spent on unnecessary air calibrations, and ensuring that the frequency of air calibrations is sufficient to guarantee correct calibration for each imaging scan.

[0016] Another advantage lies in reducing the cancellation of patient scans due to unplanned downtime.

[0017] A given embodiment may not provide any of the foregoing advantages, provide one of the foregoing advantages, provide two or more of the foregoing advantages, or provide all of the foregoing advantages, and / or may provide other advantages that will be apparent to those of ordinary skill in the art upon reading and understanding this disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] This disclosure may take the form of various components and arrangements of components and various steps and arrangements of steps. The drawings are for the purpose of illustrating only the preferred embodiments and should not be construed as limiting this disclosure.

[0019] Figure 1 An X-ray imaging device according to this disclosure is schematically shown.

[0020] Figure 2 Schematically shown is the use of Figure 1 an X-ray device monitoring method for an X-ray imaging device. DETAILED DESCRIPTION

[0021] During the normal operation of an X-ray imaging system, for example, an air calibration scan is performed weekly for a CT scanner. The air calibration scan is performed with nothing loaded in the gantry (hence, an "air" scan), but the system is otherwise set up for an imaging session. For example, any X-ray filters used for imaging a patient are in place (e.g., a dose filter, a wedge filter, a bowtie filter, etc.). The air calibration scan is used to generate a normalization factor for normalizing the measured intensities during patient imaging.

[0022] The following discloses using this existing air calibration data to monitor the health of an imaging system. Advantageously, this does not involve adding any new sensors to the system, does not include collecting any new (type of) data, and does not require any additional effort on the part of the imaging system personnel. Instead, the air calibration is compared with one or more previous air calibrations to detect changes that may indicate a developing problem with the imaging system. Since this air calibration has been performed, the data collection framework already exists and is in normal use. Additionally, since there is no patient loaded in the gantry and only air is scanned, the air scan does not contain any patient information, which would otherwise pose a privacy issue for the use of the data for system monitoring. As an example of using air calibration scans for equipment monitoring, if the detector signals of all the X-ray detectors in a detector array decrease over time, this can indicate a problem with the X-ray tube. On the other hand, if the detector signals of a subset of the detectors corresponding to a single detector module decrease over time, this may indicate a failure of the detector module. As another example, in the case of a CT scanner, air calibration data is acquired for each angular position because the detected intensity depends on the gantry angle. Heavy components on the gantry deform the gantry, and thereby the distance between the tube and the detectors changes, and thus the detected detector signal intensity changes. If the detector signal increases over time according to the change in the gantry angle, this can indicate a gantry problem, such as bearing fatigue and / or imbalance in the gantry.

[0023] In some embodiments, an X-ray imaging system health analysis can be performed each time an air calibration scan is conducted. The analysis can be performed locally, and the results can be presented on the display of the imaging device controller along with the results of other air calibration scans. In another embodiment, the air calibration data can be uploaded to a vendor server along with other machine log data and an analysis performed in a remote server or a cloud server, where any issues are reported to a remote service engineer (RSE), etc. In some embodiments, if a local analysis of the air calibration data detects an urgent problem, this can be output as an emergency alert.

[0024] In some embodiments, early detection of component problems can be based on comparing a current air scan with a previous air scan to detect changes, or can be based on comparing two or more consecutive air scans to detect trends in the data. This approach presupposes that previous air scan data is stored. However, air calibration scans generate a large amount of data. For example, in a non-limiting illustrative example of a commercial CT scanner, each detector makes measurements at a large number of gantry positions (or “views,” e.g., 2320 views in some commercial CT scanners), and there are thousands of detectors in the X-ray detector array. Thus, during normal operation, air calibration scan data is typically rewritten periodically because it is only used once to generate normalization factors. To implement the disclosed X-ray imaging system health monitoring, all or some subset of the air calibration data is stored locally or remotely for an extended period. In one approach, every Nth calibration is stored. Additionally or alternatively, the raw air calibration data can be processed to extract a smaller set of features for use in system health monitoring, which can reduce the amount of data stored long term. For example, only a subset of the 2320 views of the illustrative example can be stored, e.g., one out of every ten views around a 360° rotation, thereby reducing the size of the stored data set to one-tenth of the original data acquired.

[0025] Reference Figure 1 , an illustrative medical system including a medical device 1 is shown. The medical device 1 can be an X-ray imaging device, such as, for example, a computed tomography (CT) imaging device (as shown), or a C-arm imaging device, such as sometimes used for cardiac imaging, or an image-guided therapy (IGT) system employing X-ray imaging, a fluoroscopic imaging device, a digital radiography (DR) imaging device, or other X-ray imaging devices that utilize X-ray imaging (hereinafter referred to as “X-ray imaging device” or variants thereof). More generally, the medical device 1 can be any medical device having components for which calibration can be performed to monitor the components, such as a linear accelerator (LINAC). As Figure 1 shown, the medical X-ray device 1 can include components, such as an X-ray tube 10 shown by removal of a portion of the gantry 12 of the CT scanner 1 in Figure 1 . The X-ray tube 10 shown schematically is a simplified representation, and modern commercial X-ray tubes used in X-ray imaging devices typically include additional components, such as grids, the geometry and electrical biasing of which can be used to control the shape, focus, intensity, or other characteristics of the X-ray beam, and such components can introduce additional X-ray tube performance variables, such as grid voltage. The X-ray device 1 also includes a device controller 14 or is operably communicable with a device controller 14, the device controller being configured to control the operation of the X-ray imaging device 1.

[0026] The X-ray imaging apparatus 1 further includes an X-ray detector 16 configured to detect X-ray radiation emitted by the X-ray tube 10 after the X-ray has passed through the examination area 17. During the operation of acquiring imaging data of a patient or other imaging object (not shown), the imaging object is disposed in the examination area 17. On the other hand, during the air calibration scan, the examination area 17 is emptied so that the examination area 17 contains only air. As Figure 1 shown, the detector 16 generally includes a detector array, and the X-ray tube 10 emits a cone beam of X-rays that passes through the examination area 17 and thus impinges on the detector array 16. The detector 16 is also in electronic communication with the apparatus controller 14 (such as a workstation computer, or more generally, a computer). The image generated by the X-ray radiation produced by the X-ray apparatus 1 via the X-ray tube 10 is processed by the apparatus controller 14 and / or another electronic processing device 18, which can be implemented, for example, as the server computer 18 shown in the figure. The illustrative CT scanner 1 employs tomographic imaging, in which the X-ray tube 10 and the detector 16 jointly rotate around the imaging object to acquire a three-dimensional (3D) image of the object. In other types of X-ray imaging apparatuses, these components may be fixed in place rather than rotating around the imaging object, and thus provide a two-dimensional (2D) image. In a C-arm configuration such as sometimes used in X-ray imaging systems for cardiac imaging, image-guided therapy (IGT), or other clinical applications, the X-ray tube 10 and the detector 16 can be moved on a robotic arm or the like to different advantageous points (referred to as "views") around the patient to (for example) provide a clinically significant view of the heart, or in IGT to provide a selected view of an intervention procedure.

[0027] The electronic processing device 18 is an optional component, which may include a workstation, a server computer (as shown), or multiple server computers, such as interconnected to form a server cluster, cloud computing resources, various combinations thereof, etc., to perform more complex computing tasks. For example, in a common configuration, the device controller 14 is provided to control the imaging device 1 to perform image acquisition and also record machine log data (e.g., operation parameters of the X-ray imaging device 1, alerts, errors generated by the X-ray imaging device 1, etc.; in some embodiments disclosed herein, the log data may also include air calibration data or a subset thereof or features derived therefrom); while the server 18 is connected via a hospital network and / or the Internet to occasionally receive updates of the machine log data (which may include air calibration data or a subset thereof or features derived therefrom in some embodiments disclosed herein). The device controller 14 and / or the server 18 include typical components, such as an electronic processor 20 (e.g., a microprocessor), at least one user input device (e.g., a mouse, a keyboard, a trackball, etc.) 22, and a display device 24 (e.g., an LCD monitor, a plasma monitor, a cathode ray tube monitor, etc.).

[0028] The electronic processor 20 is operably connected to one or more non-transitory storage media 26. As a non-limiting illustrative example, the non-transitory storage media 26 may include one or more of a magnetic disk, a RAID, or other magnetic storage media; a solid state drive, a flash drive, an electrically erasable read-only memory (EEROM), or other electronic memories; an optical disc or other optical storage devices; various combinations thereof; and may be, for example, a network storage device, an internal hard disk drive of the workstation 18, various combinations thereof, etc. It should be understood that any reference herein to one or more non-transitory media 26 will be broadly construed to cover a single medium or multiple media of the same or different types. Similarly, the electronic processor 20 may be embodied as a single electronic processor or two or more electronic processors. The non-transitory storage media 26 stores instructions executable by at least one electronic processor 20. The instructions include instructions for generating a visualization of a graphical user interface (GUI) 28 for display on the display device 24.

[0029] The disclosed imaging system is also configured as described above to perform a method or process 100 for monitoring a medical device. Although described herein as the medical device being an X-ray device 1 and the component being one of the X-ray tube 10, gantry 12, and / or detector 16, method 100 can be applied to any suitable component of any suitable medical device where the performance of the component deviates from its expected performance (e.g., calibration data). A non-transitory storage medium 26 stores instructions readable and executable by at least one electronic processor 20 to perform the disclosed operations including performing the monitoring method or process 100. Depending on the processing capabilities of the device controller 14 and the availability of a server or other additional computing resources 18, the imaging device controller 14, server 18, or both can be used to perform the monitoring 100 of the health of the X-ray imaging device 1. In a suitable example, the device controller 14 controls the X-ray imaging device 1 to acquire an air calibration and processes the air calibration data to generate a normalization factor for normalizing the intensities measured during patient imaging; while the X-ray device monitoring method 100 can be performed by the imaging device controller 14 or the server 18. In some examples, method 100 can be performed at least in part by cloud processing.

[0030] Reference Figure 2, Illustrative embodiments of an example of monitoring method 100 are schematically shown as a flowchart. To begin method 100, a calibration process is performed. At operation 102, the controller 14 is configured to control the X-ray imaging device 1 to acquire an air calibration. In the air calibration, the examination area 17 of the X-ray imaging device 1 is not loaded, such that the X-rays emitted by the X-ray tube 10 pass through the air in the examination area 17 and are thus detected by the X-ray detector array 16. Thus, the air calibration data does not contain any patient information. When the examination area 17 is unloaded, one or more X-ray beam shaping components may be set in the path of the X-rays, such as a bowtie filter (also known as a wedge filter), a collimator, etc., depending on the detailed air calibration being performed. For example, if an air calibration is performed to calibrate a patient imaging sequence that typically uses a bowtie filter, the bowtie filter is appropriately installed during the collection of the air calibration data. The set of scan parameters (e.g., kV, mA, slice thickness, rotation time, focus, wedge / filter / collimator settings, etc.) needs to perform the corresponding air calibration with the same parameter settings. Since no patient is loaded, ideally, the intensity measured by the detectors of the detector array 16 should be the same across the detector array 16 and, in the illustrative case of the CT scanner 1, should also be the same for each of the (e.g., 2320) views acquired as the gantry 12 rotates the X-ray tube 10 and the detector array 16 together. However, in practice, there may be non-uniformities due to variations in detector sensitivity across the detector array 16, spatial variations in X-ray beam intensity, defects or displacements in the bowtie filter, wedge filter, or other X-ray beam shaping component(s), etc.

[0031] At operation 104, the controller 14 is configured to use the acquired air calibration to determine a gain normalization factor for the X-ray detector 16. The gain normalization factor compensates for non-uniformities such as variations in detector sensitivity across the detector array 16, spatial variations in X-ray beam intensity, defects in the bowtie filter, wedge filter, or other X-ray beam shaping component(s), etc. The gain normalization factor for the X-ray detector is appropriately stored in the non-transitory storage medium 26 for patient imaging. The air calibration 102, 104 may be performed weekly or at other specified calibration intervals to periodically update the gain normalization factor.

[0032] At operation 106, the controller 14 is configured to control the X-ray imaging device 1 to acquire an image of an object using the gain normalization factor determined in the most recent occurrence of the air calibrations 102, 104. In this way, various non-uniformities are compensated for by the most recent gain normalization factor determined in the most recent occurrence of operation 104, such as variations in detector sensitivity across the detector array 16, spatial variations in the X-ray beam intensity, defects in the bowtie filter, wedge filter, or other X-ray beam shaping components, etc. Although Figure 2 a single instance of image acquisition 106 is shown, it should be understood that many such image examinations may be performed within a week (or other time interval) between successive repetitions of the air calibrations 102, 104.

[0033] Although the air calibrations 102, 104 are primarily performed to update the gain normalization factor, as recognized herein, the air calibration data acquired in each occurrence of operation 102 (i.e., in each air calibration) also provides data from which information regarding the health of the X-ray imaging device 1 can be extracted. In particular, significant changes in the corresponding measurements of the air calibrations between different repetitions of the air calibrations 102, 104 can be analyzed to provide an early warning of component failure. In some examples, the differences in air calibrations from the same date can be analyzed and used as an early warning (such as for comparing calibrations of different sets of settings or for comparing signals across the detector 16 or various views). For example, roughening of the focal track of the anode will result in spectral hardening, which will manifest as enhanced intensity variations across various detector slices (due to variations in the amount of anode material traversed by the radiation as it exits the anode). After such roughening, air calibrations for different slice thicknesses and over time can be compared. Comparison of air calibration data for different parameters (e.g., kV, mA, field of view, and focal settings) can provide information regarding focal changes (e.g., focal position). Comparison of data from air calibrations at different gantry speeds and gantry tilt angles can provide information regarding gantry bearings and potential gantry wobble, gantry imbalance, loose gantry components, and the state of the anode bearings. Potential scout scan (overview) air calibrations in the AP (anterior-posterior) and LR (left-right) directions can further be used for anode bearing state monitoring.

[0034] If two, three, or more repetitions of the air calibrations 102, 104 are analyzed, a trend line can be extracted from which, for example, the remaining life of a component can be estimated. Thus, at operation 108, the controller 14 is configured to store the air calibration data 32 generated by at least one air calibration in the non-transitory storage medium 26 of the electronic processing device 18. In some examples, the controller 14 is configured to store the air calibration data generated by at least two air calibrations performed at different times. In some examples, the controller 14 is configured to store the air calibration data generated by at least three air calibrations performed at different times to provide more detailed trend information. In some embodiments, operation 108 stores the entire raw air calibration data generated by operation 102. In other embodiments, operation 108 performs feature extraction, data selection, data compression, or other processing of the raw air calibration data to reduce the other large size of the raw calibration data set, thereby reducing storage requirements. In another example, the air calibration data 32 (or some subset thereof or features derived therefrom) is stored as additional log data in a log file in the non-transitory storage medium 26 of the electronic processing device 18. For example, the air calibration data 32 can be stored in a log file that stores other data (e.g., kV, mA, slice thickness, rotation time, focus, wedge / filter / collimator settings, etc.) that are typically automatically recorded during operation of the imaging device.

[0035] To implement imaging device health monitoring, method 100 includes operation 110, in which the stored air calibration data 32 is retrieved from the non-transitory storage medium 26. As previously described, the detector signal data stored at operation 108 may have been processed to generate a set of values of features based on the air calibration data and has values stored for the set of features, in which case the values stored for the set of features are appropriately retrieved in operation 110.

[0036] At operation 112, in addition to performing calibration (i.e., gain normalization in operation 104), diagnostic metrics indicating problems or states of the X-ray imaging device 1 (e.g., predicted time to failure of components) are derived based on the retrieved air calibration data 32. In addition to actively calibrating the detector gain, operation 112 also uses the air calibration data 32 to passively detect problems or states of the imaging device 1. As used herein, the term "diagnostic metric" (and its variants) refers to a measured value that can be related to a component or function of the X-ray imaging device 1, or a binary "yes / no" item related to a component of the X-ray imaging device 1. In some embodiments, air calibration data 32 for two or more air calibrations performed on the X-ray imaging device 1 at different times can be retrieved, and diagnostic metrics are derived based on differences or trends over time in the air calibration data 32 indicating problems with the X-ray imaging device 1. In a similar manner, differences and trends can be derived based on air calibration data from the same time point but from different configurations of the X-ray imaging device 1 (i.e., different calibration settings or scanner settings, such as kV, mA, slice thickness, gantry speed, tilt, C-arm direction, C-arm trajectory, axial scan direction, filter, collimator, and wedge settings, etc.). In some embodiments, the controller 14 is configured to store air calibration data 32 generated by at least two air calibrations performed using different configurations of the X-ray imaging device 1, and the electronic processor 18 is programmed to derive metrics indicating problems with the X-ray imaging device 1 based on differences between air calibrations or values derived therefrom.

[0037] In some embodiments, the diagnostic metric indicates a problem with the X-ray tube 10. For example, the diagnostic metric includes an estimated remaining time to end-of-life (EOL) of a component of the X-ray tube 10 that is less than a threshold time. In another example, the diagnostic metric includes a change in the intensity, spectrum, X-ray intensity, or focal position of the X-ray tube 10. In some embodiments, the diagnostic metric indicates a problem with the X-ray detector 16. For example, the diagnostic metric includes an estimated remaining time to end-of-life (EOL) of the X-ray detector 16 that is less than a threshold time. The diagnostic metric can also include differences between detector pixels or modules, indicating that certain modules need to be swapped or replaced with each other, or indicating that certain parts of the detector 16 are decolorized or contaminated with, for example, contrast spillover.

[0038] In some embodiments, diagnostic metrics indicate problems with the gantry 12. For example, diagnostic metrics include changes in the linearity, stability, angle, or position of the gantry 12. Various methods can be used to determine what type of component problem is indicated by differences or trends in air calibration data (or features derived therefrom). For example, if all detector intensities decrease at a similar rate over time (and similarly for all views or positions of the X-ray detectors in the case of a CT or C-arm where the detectors are moving), this can be inferred to indicate a problem with the X-ray tube 10, since a single X-ray tube 10 irradiates all detectors 16. On the other hand, if only some of the X-ray detectors in the array 16 exhibit a decrease in intensity, this can be inferred to indicate a problem with those X-ray detectors, or a problem with the positioning or spectral hardening of the X-ray tube 10. If all detectors exhibiting a decrease in intensity belong to a single X-ray detector module or group of modules, this can more specifically enable an inference that there is a problem with that module or group of modules. As yet another example, there may be cyclic variations in the measured intensities that are consistent with a 360° rotation of the gantry 12. If this variation is observed to increase over time, this can be inferred to indicate a problem with the stiffness, stability, or positioning of the rotating gantry 12 or displacement of the gantry components. Forces on the gantry components vary with gantry speed, tilt, and position, which can provide additional information about the gantry components and the state of the anode bearings. Other problems that can be detected are, for example, misalignment of the patient table, misalignment of the anti-scatter grid on the detector, misalignment of the collimator or collimator components, cracks in the bowtie filter, etc. Advantageously, such inferences are not mutually exclusive. For example, an overall decrease in the observed intensity plus a larger decrease for a certain subset of detectors in the detector array 16 can enable an inference of a problem with the X-ray tube 10 and a problem with the detector subset; and cyclic variations with the rotation of the gantry 12 can also be observed and used for additional component and function characterization. These are merely examples and should not be construed as limiting.

[0039] At operation 114, an alert or status indicator 30 is output based on the derived diagnostic metrics, indicating a problem or status of the X-ray imaging device 1 determined in step 112 based on the air calibration data 32. In some examples, the alert 30 includes a recommendation to replace a component of the medical device 1 (i.e., the X-ray tube 10, the detector 16, etc.). In some examples, certain combinations of settings (e.g., high-power tube strings) can be avoided, such as swapping two detector modules, updating the system software, performing additional calibration or adjustment. In other examples, the alert 30 is output on the display device 24 of the electronic processing device 18 and / or on the display device of a remote monitoring workstation. To this end, the remote monitoring workstation receives the alert from a queue of medical devices including the medical device 1 and outputs a representation of the alert from the queue of medical devices on the GUI 28. In another example, a log file of different scan parameters for the air calibration data 32 and / or subset data defined therefrom or features derived therefrom can be transmitted to a remote service center to analyze the alert or status indicator 30 indicating a problem or status of the X-ray imaging device 1. In some embodiments, the log data transmitted to the remote service center is stored at the remote service center providing service for the X-ray imaging device 1, and operations 110, 112, and 114 are performed at the remote service center. In this method, the air calibration data 32 (or a subset or features derived therefrom) is retrieved from the transmitted log data stored at the remote service center, and the derivation of the diagnostic metrics and the output of the alert or status indicator 30 are performed at the remote service center.

[0040] In some embodiments, in cases where a device failure may be attributed to different root causes, operation 112 can additionally derive information about the root cause of the detected problem to provide a differential diagnosis indicating which part has failed to cause the detected problem. For example, a decrease in X-ray beam intensity over time may be due to a failure of the X-ray tube, or may be due to a failure of the high voltage (HV) generator powering the X-ray tube 10. These different failure modes are detectable in the trends of the air calibration data (and / or in air calibrations performed with different configurations of the X-ray imaging device 1), such as using a machine learning (ML) component trained on a labeled historical example of air calibration data over time for an X-ray system with a failed X-ray tube and a failed HV generator, such that the trained ML component can distinguish between these two component failure scenarios.

[0041] Example

[0042] A CT scanner creates three-dimensional (3D) images by reconstructing X-ray attenuation data acquired at multiple perspectives. Various corrections are applied to the raw attenuation data to obtain an artifact-free image that accurately represents the patient being scanned. For example, proper calibration for each scan is required to correct for variations in scanner settings, X-ray tube output, and attenuation characteristics. To this end, a "phantom calibration" is performed routinely (i.e., weekly) using an air phantom to obtain the initial intensity of each detector pixel (including, for example, a bowtie filter). Each set of scan parameters (kV, mA, slice thickness, gantry rotation time, focus, wedge / filter / collimator settings) will require a corresponding air calibration under exactly the same parameter settings. The resulting air calibration vectors indicate the relative efficiency and gain of the detector pixels and the variation of the X-ray beam intensity across the radiation field. They are used to normalize the attenuation data acquired during patient scans. After this normalization, the detector signal is uniform across all detector pixels. This process is similar in all X-ray imaging systems where imaging is used to some extent for quantification.

[0043] The disclosed X-ray system uses any image correction variations over time to monitor system and X-ray tube status, wear, and degradation. The image corrections contained in the air calibration vectors will change over time and gantry position, and these changes will contain indications of defects such as wear, leakage, and imbalance. Due to the existence of air vectors for various scan parameter sets, the available information content is quite large. Air vector data from direct measurements and from incremental manipulations can be used.

[0044] Typically, the air vector readings are recorded and normalized using a reference detector reading, and then compressed to save memory on the host computer. A common compression method is to use the average of a specific number 10 < N < 20 sectors of the gantry, for example, to obtain N = 16 air vectors / gantry rotation from the raw air vector / acquisition view.

[0045] The recorded raw normalized data or normalized compressed air vectors can be used by the disclosed system for monitoring. Metrics such as the distance from (one or more) previous / first / earlier air vectors, vector magnitude, norm, SNR, and corresponding metrics for frequency-transformed vectors can be used. In addition, the raw reference detector signal or its inverse can be used for monitoring (differences from previous signals, magnitude, norm, SNR).

[0046] Typical air calibration data can include the voltage of the X-ray tube 10, the current of the X-ray tube 10, collimation coverage, focus size, resolution, wedge dose filter, gantry rotation time, additional filters, etc.

[0047] The disclosed system uses non-static image correction data to monitor for defects, perturbations, or changes in the form of material fatigue, component wear, and leakage in the X-ray device 1, resulting in, for example, vibrations, wobbles, noises, and changes in, for example, image resolution, image quantization, X-ray intensity, and focal spot characteristics (such as position, uniformity, and homogeneity).

[0048] The collected air calibration data 32 is detailed low-level detector data for analysis at multiple scales from detailed to macroscopic, including, for example, identifying bad detector modules / pixels for direct service notification (e.g., based on deviation, rate of change of values, and noise); monitoring various types of global detector changes (e.g., temperature in the gantry 12 or detector 16); monitoring changes according to gantry angle (e.g., for detecting balance changes and looseness of parts, other changes outside the norm may indicate other types of faults); monitoring the status of the plastic bowtie filter (e.g., detecting (developing) cracks); monitoring beam hardening and intensity changes as the X-ray tube 10 ages, monitoring the detector 16 (i.e., identifying shadows and misalignments); recommending the date of the next air calibration (e.g., whether the detector gain is changing); and so on.

[0049] The information contained in the air calibration vector can be used in several ways for system status monitoring, such as using the distance of each detector pixel (e.g., Euclidean, Hamming, Minkowski, Jaccard, Dice, etc.) to the last corresponding air vector as a measure of system change / wear / deterioration since the last air calibration; using the distance of each pixel to the previous air vector as a measure of system wear / deterioration since the last air calibration; using the air vector range, standard deviation, mean, median, etc.; using the air vector size or (absolute) norm; using the air vector noise, such as signal-to-noise ratio (SNR) or integrated noise spectrum; using the Hounsfield or CT number of air calculated from the air vector values; using the reference detector normalized or non-normalized air vector, or just using the reference detector signal; using a subset or all of the air vector elements; using 10 - 20 compressed air vectors or the original number of vectors (uncompressed) per gantry rotation; using the fast Fourier transform (FFT) of the air calibration signal in combination with any of the methods listed above to follow the development of frequency peaks over time and rotation (this only allows for a frequency response of e.g., 10 Hz at a 0.5 s gantry rotation time); using the spatial variation on the patient detector, such as comparing values at the left, right, and center; etc. The start of sampling can be strictly examined to characterize overshoot and stabilization of, e.g., kV and mA, which can give information about the high voltage generator status. These can be quantified, characterized, and followed in a similar manner to the air vectors described above. Two DFS foci can be compared. The per-pixel difference between two focal spots can be calculated and compared to a previous table to detect changes in the focal spot deflection unit. It is even possible to use air vector metrics (e.g., absolute Euclidean norm) to detect problems without reverting to a reference previous or original installed air calibration. This may be the case, for example, when examining differences between DFS settings, focal spot sizes, different kV settings, etc.

[0050] Any cross-comparison can be used for monitoring and early problem detection. Calibration can be performed using combinations of focal spot size, gantry speed, kV, and filtration under various scan conditions. Any conceivable difference / distance / ratio can be calculated and used for monitoring the tube and system status. For example, the Euclidean distance between air vectors acquired at high and low gantry speeds can be used as an indication of imbalance or anomaly. In the same way, air vectors from a large focal spot to a small focal spot can be used to detect focal spot problems, etc.

[0051] In an imaging system that employs a rotating gantry for 3D imaging, gantry rotation produces a sinusoidal variation in the detector signals from each pixel of the patient detector and the reference detector. The sinusoidal signals from the reference detector and from the pixels at various locations on the patient detector can be compared, particularly their amplitudes. When the differences are unwrapped, this indicates a gantry or tube problem. Any other corrections that vary during the life of the X-ray tube (e.g., defocus radiation correction) can also be used for monitoring.

[0052] To save storage on the CT scanner host computer, the compressed air vector is continuously overwritten with the most recent vector. To still be able to compare with the previous vector, several ways can be envisioned. The previous air vector can be saved on the host or remotely in the cloud / computer / server. Alternatively, certain features calculated only based on the previous air vector or only the differences with the corresponding previous vector can be saved locally or remotely.

[0053] To use the fast Fourier transform (FFT) of the detector signals, the development of the peaks (i.e., the appearance, disappearance, frequency, amplitude, or AUC over time) can be used to monitor the X-ray tube 10 and other system components (gantry 12, generator, detector 16, fan, cooling, pump, heat exchanger, cables, etc.). For the X-ray tube 10, anode rotation and wear (FFT peak height or area), focal spot degradation (e.g., position), bearing rotation and wear, various drive frequencies such as mains and supply voltage with ripple (gantry drive, power module, grid, filament, tube, anode drive, detector), sampling rate, slip, and duty cycle can be monitored. The peaks corresponding to the mechanical vibrations of the tube emitter (coil or flat emitter) can change over time due to material evaporation (i.e., filament wear). On the anode side, the peaks emitted from the anode rotation will increase in amplitude due to, for example, anode imbalance and wobbling. For ball and spiral groove bearings, the bearing condition and wear can also be reflected in the FFT spectrum of the detector signal, e.g., as a frequency shift, higher harmonics of the rotational frequency, which is due to, for example, lubricant loss, track wear, and anode motor drive slip. For a slotted anode, the slots can create additional diagnostic possibilities. The positions of the anode and filament peaks can shift slightly due to temperature changes, e.g., reflecting instantaneous tube usage. However, since air calibration is most often done directly after warm-up, the temperature changes should have a limited impact.

[0054] Detected deviations from the previous air calibration can also indicate a deterioration of the overall image quality. In this case, appropriate maintenance actions can include scheduling and performing a full system calibration by a service engineer at a time point that has a minimal impact on the normal workflow.

[0055] The disclosed method can be understood as handcrafted features. These features can be used to train neural networks or other (machine learning) algorithms to detect faults. The corresponding training data will consist of the extracted latent features and actual faults and / or system problems. Different from using analytically predefined detection methods or algorithms (handcrafted features), all data can be fed into a (deep) learning algorithm (e.g., convolutional neural network) together with the faults / system problems as labels (results).

[0056] The disclosed systems and methods are applicable to CT, cone beam CT / C-arm systems, characterized, for example, by an X-ray tube with ball bearings, which is too costly for additional sensors. Use in other imaging systems (such as any cardiovascular system, PET-CT, SPECT-CT, MR-CT, planar X-ray, mammography, and linear scanning systems for, e.g., luggage scanning) is also envisioned. Once the conventional air calibration of the X-ray imaging system is adopted, the calibration data can be utilized for system monitoring.

[0057] The present disclosure has been described with reference to preferred embodiments. Others may make modifications and alterations upon reading and understanding the foregoing detailed description. The exemplary embodiments are intended to include all such modifications and variations as long as they fall within the scope of the appended claims or their equivalents.

Claims

1. A non-transitory computer-readable medium (26) storing instructions that can be executed by at least one electronic processor (20) to perform a method (100) for monitoring an X-ray imaging device (1), the method comprising: Retrieving air calibration data (32) generated by at least one air calibration performed on the X-ray imaging device; Deriving a diagnostic metric indicating a problem or a state of the X-ray imaging device based on the retrieved air calibration data; And Outputting an alert or a status indicator (30) indicating the problem or the state of the X-ray imaging device based on the derived diagnostic metric.

2. The non-transitory computer-readable medium (26) according to claim 1, wherein, The diagnostic metric indicates a problem or a state of an X-ray tube (10) of the X-ray imaging device (1).

3. The non-transitory computer-readable medium (26) according to claim 1, wherein, The diagnostic metric indicates a problem or a state of an X-ray detector (16) of the X-ray imaging device (1).

4. The non-transitory computer-readable medium (26) according to any one of claims 1-3, wherein, The method (100) further comprises: Using the air calibration to determine an X-ray detector gain normalization factor.

5. The non-transitory computer-readable medium (26) according to claim 1, wherein, The diagnostic metric indicates a problem or a state of a gantry (12) of the X-ray imaging device (1).

6. The non-transitory computer-readable medium (26) according to any one of claims 1-5, wherein: The diagnostic metric includes that an estimated remaining time until the end of life (EOL) of a component of the X-ray imaging device (1) is less than a threshold time.

7. The non-transitory computer-readable medium (26) according to any one of claims 1-6, wherein: The retrieving includes retrieving air calibration data of two or more air calibrations performed on the X-ray imaging device (1) at different times; and The diagnostic metric is derived based on a trend over time of the air calibration data indicating the problem of the X-ray imaging device.

8. The non-transitory computer-readable medium (26) according to any one of claims 1-6, wherein: The retrieving includes retrieving air calibration data of two or more air calibrations performed on the X-ray imaging device (1) with different configurations of the X-ray imaging device; and The diagnostic metric is derived based on a difference between the two or more air calibrations indicating the problem of the X-ray imaging device or values derived therefrom.

9. The non-transitory computer-readable medium (26) according to any one of claims 1-8, wherein, The method (100) further comprises: Processing detector signal data collected during the at least one air calibration to generate values for a set of features according to the air calibration data, and storing the values for the set of features; wherein the retrieving of the air calibration data (32) generated by the at least one air calibration includes retrieving the stored values for the set of features.

10. The non-transitory computer-readable medium (26) according to any one of claims 1-9, wherein, The method (100) further comprises: Controlling the X-ray imaging device (1) to collect the air calibration data generated by the at least one air calibration; and Storing the air calibration data obtained by the control.

11. The non-transitory computer-readable medium (26) according to any one of claims 1-10, further comprising: Store log data generated by the X-ray imaging device, the log data including operating parameters of the X-ray imaging device and further including the air calibration data (32) or a subset thereof or features derived therefrom; And Transmit the stored log data to a remote service center; Wherein, the retrieval of the air calibration data (32) includes retrieving the air calibration data (32) or the subset thereof or the features derived therefrom from the stored log data.

12. The non-transitory computer-readable medium (26) according to any one of claims 1-10, further comprising: Store log data generated by the X-ray imaging device, the log data including operating parameters of the X-ray imaging device and further including the air calibration data (32) or a subset thereof or features derived therefrom; And Transmit the stored log data to a remote service center and store the transmitted log data at the remote service center; Wherein, the retrieval of the air calibration data (32) includes retrieving the air calibration data (32) or the subset thereof or the features derived therefrom from the transmitted log data stored at the remote service center, and performing the derivation and output at the remote service center.

13. The non-transitory computer-readable medium (26) according to any one of claims 1-12, wherein, Outputting the alert (30) includes: Outputting the alert as a recommendation to replace a component of the medical device (1).

14. The non-transitory computer-readable medium (26) according to claim 13, wherein, A remote monitoring workstation (18) receives an alert from a queue of medical devices including the medical device (1), and the method (100) further includes: Presenting a representation of the alert from the queue of medical devices on a graphical user interface (GUI) (28) provided on a display device (24).

15. An X-ray imaging system, comprising: An X-ray imaging device (1); A controller (14) configured to: Control the X-ray imaging device to acquire an air calibration; Use the air calibration to determine a gain normalization factor for an X-ray detector (16) of the X-ray imaging device; Control the X-ray imaging device to acquire an image of an associated object using the determined gain normalization factor; and Store air calibration data (32) generated by at least one air calibration; And An electronic processor (18) programmed to: Retrieve the stored air calibration data; Derive a diagnostic metric indicating a problem or status of the X-ray imaging device based on the retrieved air calibration data; And Output an alert (30) indicating the problem or status of the X-ray imaging device based on the derived diagnostic metric.

16. The X-ray imaging system according to claim 15, wherein, The controller (14) is configured to store the air calibration data (32) as features extracted therefrom.

17. The X-ray imaging system according to any one of claims 15 and 16, wherein, The controller (14) is configured to store air calibration data (32) generated by at least two air calibrations performed at different times, and the electronic processor (18) is programmed to derive the metric indicating the problem or status of the X-ray imaging device (1) based on a trend over time in the air calibration data.

18. The X-ray imaging system according to any one of claims 15-17, wherein, The controller (14) is configured to store air calibration data (32) generated by at least two air calibrations performed with different configurations of the X-ray imaging device (1), and the electronic processor (18) is programmed to derive the metric indicating the problem of the X-ray imaging device (1) based on a difference between the air calibrations or values derived therefrom.

19. A non-transitory computer-readable medium (26) storing instructions that can be run by at least one electronic processor (20) to perform a method (100) for monitoring an X-ray device (1), the method comprising: retrieving air calibration data (32) generated by at least one air calibration performed for the X-ray device; deriving a diagnostic metric indicating a problem or a state of the X-ray device from the retrieved air calibration data; and outputting an alert (30) indicating the problem or the state of the X-ray device based on the derived diagnostic metric.

20. The non-transitory computer-readable medium (26) according to claim 19, wherein: the retrieved air calibration data (32) includes X-ray imaging device calibration data generated by calibrating the X-ray imaging device (1); and the diagnostic metric is derived from the X-ray imaging device calibration data.

Images