MAGNETIC RESONANCE EXAMINATION SYSTEM WITH PREFERRED SETTINGS BASED ON DATA MINING

FIELD OF THE INVENTIONThe invention relates to a method of performing a magnetic resonance imaging scan using an MR scanner, a method of providing statistical information to a magnetic resonance imaging scanner, a computer program product, a magnetic resonance imaging scanner for performing a magnetic resonance imaging scan and a database system.BACKGROUND OF THE INVENTIONImage-forming MR methods, which utilize the interaction between magnetic field and nuclear spins in order to form two-dimensional or three-dimensional images are widely used nowadays, notably in the field of medical diagnostics, because for the imaging of soft tissue they are superior to other imaging methods in many respects, they do not require ionizing radiation, and they are usually not invasive.According to the MR method in general, the body of a patient or in general an object to be examined is arranged in a strong, uniform magnetic field B0 whose direction at the same time defines an axis, normally the z-axis, of the coordinate system on which the measurement is based.The magnetic field produces different energy levels for the individual nuclear spins in dependence on the applied magnetic field strength which spins can be excited (spin resonance) by application of an alternating electromagnetic field (RF field) of defined frequency, the so called Larmor frequency or MR frequency. From a macroscopic point of view the distribution of the individual nuclear spins produces an overall magnetization which can be deflected out of the state of equilibrium by application of an electromagnetic pulse of appropriate frequency (RF pulse) while the magnetic field extends perpendicularly to the z-axis, so that the magnetization performs a precessional motion about the z-axis.Any variation of the magnetization can be detected by means of receiving RF antennas, which are arranged and oriented within an examination volume of the MR device in such a manner that the variation of the magnetization is measured in the direction perpendicularly to the z-axis.In order to realize spatial resolution in the body, switching magnetic field gradients extending along the three main axes are superposed on the uniform magnetic field, leading to a linear spatial dependency of the spin resonance frequency. The signal picked up in the receiving antennas then contains components of different frequencies which can be associated with different locations in the body.The signal data obtained via the receiving antennas corresponds to the spatial frequency domain and is called k-space data. The k-space data usually includes multiple lines acquired with different phase encoding. Each line is digitized by collecting a number of samples. A set of samples of k-space data is converted to an MR image, e.g. by means of Fourier transformation.The above description of performing magnetic resonance imaging provides a brief impression on the plurality of parameters which may be adjusted in order to obtain an MR image of a desired portion of the object to be imaged at a desired quality.Typically, an MR scan protocol used for adjustment of the conditions to be used when performing a magnetic resonance imaging scan can consist of more than 150 adjustable parameters. With the continuing advances in MR sequence development, it is expected that even more methods become available and need to be parameterized in the user interface used at the MR scanner to provide the relevant MR scan protocol parameters to the scanner.Moreover, radiologists and technicians frequently need to work on different MR systems, from different vendors and are familiar with the user interface of a presently used MR system only up to a certain degree. As a consequence, in these conditions the optimal choice of scan parameters is a difficult, tedious and often iterative task, even for expert users. As a consequence, many scans need to be repeated until image quality is judged good enough. In other cases, the appropriate choice of scan parameters results in inferior image quality below the requested quality standards. Another consequence is that advanced imaging techniques are not used as often as they could be, because the technician may not be aware of the suitable techniques to solve a particular image quality problem or to address a particular patient imaging need.US 7,315,755discloses a system and method for communicating a protocol over a network. More specifically, this document relates to a protocol/medical image registration method that permits centralized management of pairs of protocol and a medical image, wherein numerous user terminals are permitted to share protocols as common resources. Consequently, this method permits to make imaging protocols available, howeverwith the drawback that only 'prefabricated' protocols are provided, such that with respect to the individual circumstances with respect to an imaging procedure a user is still required to adapt the scan parameters of the selected MR scan protocol in an individual manner. Consequently, the optimal choice of scan parameters is still difficult even for expert users.EP 1 354 554 A2refers to a networked scanner environment wherein each scanner is communicable with one or more databases configured to store data associated with previously executed imaging sessions. The databases may be queried by a user to determine, based on a set of user inputs, an historical evaluation of the prior imaging sessions conducted in accordance with scan parameters similar to the scan parameters of an imminent imaging session. Included is a global database that is accessible by a series of remotely located imaging systems as well as one or more databases particular to a specific treatment facility housing one or more imaging scanners.US 2008/130972 A1refers to a method of imaging. The method includes determining imaging parameters. Further, the methodincludes acquiring image data from a patient. Additionally, the method includes storing the imaging parameters with the acquired image data. The method also includes retrieving the stored imaging parameters for use in a subsequent examination. Systems and computer-readable medium that afford functionality of the type defined by this method are also contemplated in conjunction with the present technique.US 2004/148403 A1provides a technique for sharing clinical protocols for diagnostic imaging systems. The clinical protocols generally represent operational parameters, such as configuration data and procedures, which are clinically developed for a particular imaging diagnosis. An interface or access point, such as a network accessible database or website, is provided to facilitate the exchange of these clinical protocols between clinicians. The present technique also may facilitate the formation of new clinical protocols and/or the integration of new clinical protocols into various diagnostic imaging systems. Accordingly, clinicians can electronically exchange and configure a variety of imaging protocols for potentially greater quality in the particular imaging diagnosis.EP 1 229 472 A1describes an MRI system center connected to a plurality of MRI systems for visualizing the interior of a subject to be examined using a magnetic resonance phenomenon through an electronic communication line. The MRI system center receives data of a log file on which a use state of the MRI systems is recorded or use-state data extracted from the log file, from the MRI systems through a communication control unit.A database unit stores the data of the log file or the use-state data. An analysis unit analyzes the data of the log file or the use-state data received within a given period of time.From the foregoing it is readily appreciated that there is a need for an improved method of performing a magnetic resonance imaging scan. Further, there is a need for an improved magnetic resonance imaging scanner and an improved computer program product.SUMMARY OF THE INVENTIONIn accordance with the invention, a method of performing a magnetic resonance imaging scan using an MR scanner is provided in accordance with independent claim 1, the method comprising the steps of receiving an MR imaging protocol via a user interface, the MR imaging protocol being categorizable into an MR scan type of a predefined set of MR scan types, wherein the MR scan type is a generic term which permits to describe a set of specific imaging sequences which can be classified with said generic term, and the MR imaging protocol includes adjustable parameters of the MR scanner for performing the MR imaging scan using the MR scan type employed at the MR scanner for performing the MR imaging scan, querying a database by providing scan information to the database, the scan information permitting the database to identify the MR scan type of the MR imaging protocol, and providing statistical information on the MR scan type, wherein the statistical information is obtained by analysis of previous MR scans, receiving in response to said querying from the database the statistical information on the MR scan type, said statistical information comprising statistics on modifications of individual scan parameters of the adjustable parameters of the MR scan type, providing said statistical information to the user interface to provide a support at the user interface with information on parameters which may require adaption when using the selected MR imaging protocol and/or which parameter values are typically used, receiving modifications of said MR imaging protocol from the user interface, said modifications resulting in a modified MR imaging protocol, performing the MR imaging scan using the modified MR imaging protocol.It has to be noted that an 'MR scan type' is understood as for example a generic term which permits to describe a set of specific imaging sequences which can be classified with said generic term. For example, the generic term or MR scan type 'gradient echo' covers the pulse sequences coherent gradient echo (FFE), incoherent gradient echo (T1 FFE), incoherent gradient echo, steady-state free precession (T2 FFE), balanced sequence (balanced FFE), and double echo steady-state. In a further example, the MR scan typeinversion recovery' covers short T1 inversion recovery (STIR), long Tau inversion recovery (FLAIR) and true inversion recovery (Real IR).Further, an MR scan type may also categorize an MR imaging protocol with respect to different scan options used when performing an MR imaging scan. Options comprise for example the provision of saturation pulses for water and/or fat saturation, multislice imaging, single-slice imaging, three-dimensional imaging, bandwidth, magnetizationtransfer contrast, the application of partial echoes, as well as patient-specific protocols used for ECG synchronization, respiratory compensation and automatic bolus detection.As a consequence, any MR imaging protocol received via the user interface can be categorized into a certain MR scan type which in turn permits to provide an elegant possibility to provide statistical information with respect to this MR scan type, wherein the statistical information was obtained by analysis of previous MR scans.Consequently, the present invention provides a possibility to support for example a technician at a user interface with information on parameters which may require adaption when using the selected MR imaging protocol and which parameter values are typically used, i.e. are appropriate.In accordance with the invention the statistical information is based on information about previously performed MR imaging scans employing said MR scan type. More specifically, providing said statistical information to the user interface comprises indicating individual scan parameters for which the statistics on modification frequency is above a predefined threshold. In other words, the invention proposes to compute statistics on scan parameters which are most frequently adapted for a given MR scan type or protocol, wherein preferably the statistics are computed together with statistical descriptors of the parameter values, such as the modes (most frequent values), or the range. This information may then be provided to the user interface, i.e. for example displayed to the user in a suitable manner, for example while adjusting a given parameter.In accordance with a further embodiment of the invention, the statistical information comprises statistics on ranges of modifications of individual scan parameters of the scan type. For example, the statistics on ranges of modifications of individual scan parameters of the MR scan type further comprise threshold ranges for said scan parameters. Thus, based on previously performed MR imaging scans, typical ranges of scan parameters are identified, such that a user may be assisted in selecting appropriate parameter values when adapting his imaging sequence by providing these ranges. Consequently, this prevents the user to accidentally enter unusual scan parameters which are completely 'out of range'.In accordance with a further embodiment of the invention, the method further comprises receiving a modification of a scan parameter of the MR imaging protocol via the user interface, determining if the received modification of the scan parameter is outside a threshold range for said scan parameter and providing an indication to the user interface in case the received modification if outside the threshold range.Additionally or alternatively it may be possible to provide for example the threshold ranges to the user interface which has the advantage that the user is assisted in choosing the most appropriate parameters since he will intuitively select the parameters to be within the threshold range.In accordance with a further embodiment of the invention, the method further comprises providing information about the MR imaging protocol used in the imaging procedure to the database. Thus, this permits the database to use the imaging parameters used for the actual MR imaging scan to update its statistics with respect to the used MR scan type.In accordance with a further embodiment of the invention, the method further comprises categorizing the MR imaging protocol for obtaining an MR scan type of the imaging protocol, wherein the scan information comprises the obtained MR scan type. In other words, either the MR scanner itself performs the categorization and only provides the resulting MR scan type to the database, or the MR scanner provides for example the MR imaging protocol itself to the database, wherein in turn the database performs the categorization of the MR imaging protocol to determine the MR scan type associated with said MR imaging protocol.In accordance with an embodiment of the invention, the scan information comprises parameters of the MR imaging protocol and/or information on the MR scanner hardware and/or information on the MR scanner software. Consequently, this permits to identify the MR scan type more precisely adapted to the actual requirements with respect to hardware and software. Thus, besides scan protocol parameters, information on hardware and software configuration for each scan protocol like scanner type, applied magnetic field strengths, gradient type or software release number may be used to categorize in a highly precise manner the correct MR scan type.In another aspect, the invention relates to a computer program product comprising computer executable instructions to perform the method steps as described above.In another aspect, the invention relates to the magnetic resonance imaging scanner for performing the magnetic resonance imaging scan, as defined in independent claim 10.BRIEF DESCRIPTION OF THE DRAWINGSThe enclosed drawings disclose preferred embodiments of the invention. It should be understood, however, that the drawings are designed for the purpose of illustration only and not as a definition of the limits of the invention. In the drawings:Fig. 1illustrates a schematic of an MR device according to the invention,Fig. 2is a block diagram illustrating various method steps to perform the method according to the invention.DETAILED DESCRIPTION OF EMBODIMENTSWith reference toFig. 1, an MR imaging system 1 is shown. The system comprises superconducting or resistive main magnet coils 2 such that a substantially uniform, temporarily constant main magnetic field B0 is created along a z-axis through an examination volume.The magnetic resonance system applies a series of RF pulses and switched magnetic field gradients to invert or excite nuclear magnetic spins, induce magnetic resonance, refocus magnetic resonance, manipulate magnetic resonance, spatially or otherwise encode the magnetic resonance, saturate spins and the like to perform MR imaging.More specifically, a gradient pulse amplifier 3 applies current pulses to selected ones of whole body gradient coils 4, 5 and 6 along x, y and z-axes of the examination volume. An RF transmitter 7 transmits RF pulses or pulse packets, via a send/receive switch 8 to an RF antenna 9 to transmit RF pulses into the examination volume. A typical MR imaging sequence is composed of a packet of RF pulse sequences of short duration which taken together with each other and any applied magnetic field gradients achieve a selected manipulation of nuclear magnetic resonance. The RF pulses are used to saturate, excite resonance, invert magnetization, refocus resonance, or manipulate resonance and select a portion of a body 10 positioned in the examination volume. The MR signals may also be picked up by the RF antenna 9.For generation of MR images of limited regions of the body or in general object 10, for example by means of parallel imaging, a set of local array RF coils 11, 12 and13 are placed contiguous to the region selected for imaging. The array coils 11, 12 and 13 can be used to receive MR signals induced by RF transmissions effected via the RF antenna. However, it is also possible to use the array coils 11, 12 and 13 to transmit RF signals to the examination volume.The resultant MR signals are picked up by the RF antenna 9 and/or by the array of RF coils 11, 12 and 13 and are demodulated by a receiver 14 preferably including a pre-amplifier (not shown). The receiver 14 is connected to the RF coils 9, 11, 12 and 13 via a send/receive switch 8.A host computer 15 controls the gradient pulse amplifier 3 and the transmitter 7 to generate any of a plurality of imaging sequences, such as echo planar imaging (EPI), echo volume imaging, gradient and spin echo imaging,fast spin echo imaging and the like.For the selected sequence, the receiver 14 receives a single or a plurality of MR data lines in a rapid succession following each RF excitation pulse. A data acquisition system 16 performs analogue to digital conversion of the received signals and converts each MR data line to a digital format suitable for further processing. In modern MR devices the data acquisition system 16 is a separate computer which is specialized in acquisition of raw image data.Ultimately, the digital raw image data is reconstructed into an image representation by a reconstruction processor 17 which applies a Fourier transform or other appropriate reconstruction algorithms. The MR image may represent a planar slice through the patient, an array of parallel planar slices, a three-dimensional volume or the like. The image is then stored in an image memory where it may be accessed for converting slices or other portions of the image representation into appropriate formats for visualization, for example via a video monitor 18 which provides a man readable display of the resultant MR image.Further shown inFig. 1is an interface 21 connected to for example the host computer 15. The interface 21 serves for providing a communication with an external database 30. As described above, in case an MR imaging protocol is received for example via the user interface 18, the host computer 15 may either provide directly this MR imaging protocol via the interface 21 to the database 30, wherein in response to the provision of said protocol the database 30 returns statistical information comprising statistics on modification of individual scan parameters with respect to said provided MR imaging protocol.Alternatively, the host computer 15 may provide the MR imaging protocol to the categorizing component 20, which categorizes the MR imaging protocol into an MR scantype of a predefined set of MR scan types, wherein this identified MR scan type is then provided via the interface 21 to the database 30.In the following, these principles shall be discussed in greater detail with respect to the block diagram inFig. 2which illustrates various method steps with respect to the present invention.Shown inFig. 2is for example a user interface, for example a graphical user interface 18, which displays various parameters of a selected MR imaging protocol. For example, an MR imaging protocol may be stored in a database (not shown inFig. 2) comprising so called 'ExamCards', where scan protocols are optimized and stored according to the most often performed examinations with respect to the scanner 1 shown inFig. 2.However, scan protocols require adaption of a certain number of parameters to comply with patient-specific constraints. In the state of the art this is generally done by a radiology technician during the examination, while the patient is on the scan table, wherein the technician often has to cope with patient-specific problems such as motion or breathe hold length. It turned out that not only geometry parameters are routinely adapted by the technician but also parameters having an influence on image quality, scan time or contrast. The degree to which scan parameters are optimized by the user greatly varies within institutions or technicians.Examples of user interface parameters requiring more or less frequent adaption by a technician include for example the field of view, resolution, number of slices, slice gap, fold over direction, SENSE mode, SENSE reduction factor, number of averages, echo time and repetition time.The present invention uses for example data-mining techniques to find out which parameters of a given scan protocol require adaption and to provide statistical information on the values they are typically used with. The database system 30 uses log files 104 that are systematically for example stored on the MR system and sent to the database system 30 via a remote service network. These log files 104 contain the values of all user interface parameters for previously executed MR scans. The main advantage of using the log files as an information source is that parameter settings often encountered in practice are taken as a basis, as opposed to rule-based mechanisms.In the simplest form, the invention exploits the log files stemming from the MR system under consideration. However, generally it is preferred to use log files from a multitude of different MR systems and to build up a database which offers multi-site information.In a preprocessing step 106 the values of the scan parameters are extracted from the log files 104 and are organized in a database table 100 at the database system 30.However, it has to be noted here that the present invention can also be carried out by using for example only a local database system 30 associated with the MR scanner shown inFig. 2. In this case, the database table 100 is a local database table and not a global one as discussed above. In case the database system is a local database system, the values of the scan parameters may be extracted and stored in a local database table 100 of the MR system 1, possibly as a compliment to the ExamCard database.However, without loss of generality in the following it is assumed that the database system 30 is a global database system at a remote site compared to the MR scanner used inFig. 2. Data transmission between the MR scanner 1 and the database system 30 may be performed via a network like the internet.For each scan protocol contained in the database table 100, the database system 30 computes statistics on the scan parameters which are most frequently adapted for this particular protocol, together with statistical descriptors of the parameter values such as the modes (most frequent values) or the range. For this purpose, the information comprised in the log files 104 may be parsed in a suitable data structure, containing only the relevant parameters. For example this data structure may be an XML data structure. The results of the parsing operation are then stored into the database table 100. Preferably, the database system 30 collects information gathered over multiple days or weeks, and possibly from different installed scanners. Besides scan protocol parameters, the database may also store information on hardware and software configuration for each scan protocol like the scanner type, hardware configuration such as gradient type and software release number.The search for optimized protocol settings becomes active on the MR scanner 1 when an MR user loads a protocol from the ExamCard database into the scan lists and starts editing the protocol in the for example graphical user interface 18. Upon loading the protocol from the ExamCard, either the loaded protocol or an MR scan type into which the loaded MR imaging protocol is categorized is provided to the database system 30, which in turn provides statistical information 102 on this specific MR scan type to the scanner. The data-mining performed by the database system 30 on the database table 100 may be either performed 'on the fly' when receiving the MR scan type or the MR imaging protocol. Alternatively the data-mining may be performed in a preprocessing step such that the database system 30 only has to access the readily computed statistical information on the MR scan type. In the latter case, the statistical information is precomputed.Then, the statistical information is provided in step 108 to the graphical user interface 18. Herein, different functionalities may be provided at the graphical user interface 18:According to the invention, a set of scan parameters which often require adaptation, i.e. for which the statistics on modification frequency is above a predefined threshold, are displayed. These parameters may be grouped into a single parameter group or just highlighted in the whole parameter list on the graphical user interface. Further, it is possible to display statistics showing the typical values (mode or range) for a selected parameter. This functionality could become active for example only upon request by the user. Alternatively, this functionality may become active automatically in case a user starts editing a selected parameter. The statistics can be derived from the pre-computed statistics, or they may be computed on the fly, taking into account the values of all other scan parameters currently chosen.A further functionality may be displaying of a warning (or request for confirmation) for parameters being out of the typical range of utilization, once the protocol has been finalized.Consequently, the invention provides a method which permits the technician to identify in an easy and reliable manner which parameters of a given MR scan protocol may require adaption and which parameter values may be appropriate for that purpose. It has to be noted that categorizing of an MR imaging protocol into an MR scan type may be performed at different levels of complexity: categorization may be either performed, as described above, only with respect to a given type of imaging sequence which describes in a generic term different sub-groups of specialized imaging pulse sequences. However, it is additionally or alternatively possible to perform a categorization with respect to desired imaging contrast types or even with respect to specific applications.After completion of an MR scan, the logfile 104 generated by the MR system 1 upon execution of the MR scan is provided to the database system 30 for further analysis, i.e. for enabling updating the database table 100 and optionally the statistical information 102.REFERENCE NUMERALS1.MR imaging system2.main magnet coils3.gradient pulse amplifier4.whole body gradient coil5.whole body gradient coil6.whole body gradient coil7.RF transmitter8.send/receive switch9.RF antenna10.object to be imaged11.RF coil12.RF coil13.RF coil14.receiver15.host computer16.data acquisition system17.reconstruction processor18.user interface19.categorizer inferface database system100.database table102.statistics104.log file106.step.108.step See more