阅读说明：本技术 磁共振系统及其图像显示方法、计算机可读存储介质 (Magnetic resonance system, image display method thereof, and computer-readable storage medium ) 是由 曹楠 赖永传 银剑勇 于 2020-06-23 设计创作，主要内容包括：本发明的实施例提供一种磁共振系统及其图像显示方法、计算机可读存储介质。该方法包括：获取待显示的序列图像,所述序列图像包括多幅图像；针对所述多幅图像确定相同的窗宽值；以及,基于所述窗宽值显示所述序列图像的多幅图像。(The embodiment of the invention provides a magnetic resonance system, an image display method thereof and a computer readable storage medium. The method comprises the following steps: acquiring a sequence image to be displayed, wherein the sequence image comprises a plurality of images; determining a same window width value for the plurality of images; and displaying a plurality of images of the sequence of images based on the window width value.)

1. An image display method of a magnetic resonance system, comprising:

acquiring a sequence image to be displayed, wherein the sequence image comprises a plurality of images;

determining a same window width value for the plurality of images; and the number of the first and second groups,

displaying a plurality of images of the sequence of images based on the window width value.

2. The method of claim 1, wherein determining the same window width value for the plurality of images comprises:

obtaining an ordering of pixel values of the plurality of images;

and determining the window width value based on the pixel value of the ordered preset sequence number or a plurality of pixel values in a preset sequence number range.

3. The method of claim 2, wherein determining the same window width value for the plurality of images comprises:

and determining the window width value based on the pixel value of the sorted middle sequence number or a plurality of pixel values in the middle sequence number range of the middle sequence number.

4. The method of claim 1, wherein determining the window width value based on the plurality of pixel values within the intermediate sequence number range comprises: determining an average of the plurality of pixel values as the window width value.

5. The method of claim 1, wherein the method further comprises: determining an adjustment coefficient and adjusting the window width value based on the adjustment coefficient; displaying a plurality of images of the sequence of images based on the same window width value includes: displaying the plurality of images based on the adjusted window width value.

6. The method of claim 5, wherein determining an adjustment factor comprises: determining the adjustment coefficient based on one or more imaging information corresponding to the sequence of images.

7. The method of claim 6, wherein the one or more imaging information includes one or more of an imaging site, a scan sequence, a scan plane, an echo time, an inversion time, a repetition time set when the magnetic resonance system generates the sequence images.

8. The method of claim 7, wherein determining an adjustment factor comprises: inputting the one or more imaging information into a predetermined deep learning network, and outputting the adjustment coefficient through the deep learning network.

9. The method of claim 5, wherein determining the adjustment factor comprises:

determining user information when the sequence image is displayed;

a corresponding adjustment factor is determined based on the determined user information.

10. The method of claim 5, wherein determining the adjustment factor comprises:

determining user information when the sequence image is displayed;

and inputting the determined user information into a second predetermined deep learning network, and outputting the adjusting coefficient through the second deep learning network.

11. A magnetic resonance system comprising:

a scanner for generating a sequence image by performing a magnetic resonance scan of an imaging site, the sequence image comprising a plurality of images;

a processor for acquiring the sequence of images and determining a same window width value for the plurality of images; and the number of the first and second groups,

a display unit that displays a plurality of images of the sequence of images based on the same window width value.

12. A computer-readable storage medium for storing computer-readable instructions for performing the image display method of any one of claims 1 to 10.

Technical Field

The disclosed embodiments relate to medical imaging technology, and more particularly, to a magnetic resonance system, an image display method thereof, and a computer-readable storage medium.

Background

In the prior art, Magnetic Resonance Imaging (Magnetic Resonance Imaging) technology can be used to image human tissue to obtain a plurality of slice images, i.e. a sequence of images, of a region of interest. At a certain stage of the magnetic resonance examination, the image sequence needs to be displayed on a human-computer interaction interface of the magnetic resonance system according to a certain arrangement mode, so that a doctor can read and observe the image sequence conveniently. In practical applications, when a doctor reads the images of the sequence, the doctor needs to manually adjust display parameters, such as window width values, of one or more of the images through experience, often because the brightness difference between the images in the image sequence is large or the display effect cannot meet the requirements of clinical diagnosis. This way the efficiency of the magnetic resonance imaging diagnosis is affected.

Disclosure of Invention

An embodiment of the present invention provides an image display method of a magnetic resonance system, including:

acquiring a sequence image to be displayed, wherein the sequence image comprises a plurality of images;

determining a same window width value for the plurality of images; and the number of the first and second groups,

displaying a plurality of images of the sequence of images based on the window width value.

In one embodiment, determining the same window width value for the plurality of images further comprises:

acquiring the sequence of the pixel values of the plurality of images;

and determining the window width value based on the pixel value of the ordered preset sequence number or a plurality of pixel values in a preset sequence number range.

In one embodiment, the window width value is determined based on the pixel value of the sorted middle sequence number or a plurality of pixel values within the middle sequence number range in which the middle sequence number is located.

In one embodiment, determining the window width value based on the plurality of pixel values within the intermediate sequence number range comprises: an average of the plurality of pixel values is determined as the window width value.

The method may further comprise: an adjustment factor is determined and the window width value is adjusted based on the adjustment factor, in one embodiment, the plurality of images are displayed based on the adjusted window width value.

In one embodiment, the adjustment factor is determined based on one or more imaging information corresponding to the sequence of images.

Wherein the one or more imaging information includes one or more of an imaging region, a scan sequence, a scan plane, an echo time, a reversal time, and a repetition time set when the magnetic resonance system generates the sequence image.

In one embodiment, the one or more imaging information is input into a predetermined deep learning network, and the adjustment factor is output through the deep learning network.

In one embodiment, the step of determining the adjustment factor comprises:

determining user information when the sequence image is displayed;

a corresponding adjustment factor is determined based on the determined user information.

In one embodiment, the determined user information is input into a predetermined second deep learning network, and the adjustment coefficient is output through the second deep learning network.

Another embodiment of the present invention also provides a magnetic resonance system including:

a scanner for generating a sequence image by performing a magnetic resonance scan of an imaging site, the sequence image comprising a plurality of images;

a processor for acquiring the sequence of images and determining a same window width value for the plurality of images; and the number of the first and second groups,

a display unit that displays a plurality of images of the sequence of images based on the same window width value.

Another embodiment of the present invention also provides a computer-readable storage medium for storing computer-readable instructions for executing the image display method of any one of the above embodiments.

It should be understood that the brief description above is provided to introduce in simplified form some concepts that are further described in the detailed description. It is not meant to identify key or essential features of the claimed subject matter, the scope of which is defined uniquely by the claims that follow the detailed description. Furthermore, the claimed subject matter is not limited to implementations that solve any disadvantages noted above or in any section of this disclosure.

Drawings

The invention will be better understood by reading the following description of non-limiting embodiments, with reference to the attached drawings, in which:

fig. 1 shows a schematic representation of a magnetic resonance system;

FIG. 2 shows a flow diagram of an image display method according to one embodiment of the invention;

FIG. 3 shows a flow chart of an image display method according to another embodiment of the invention;

FIG. 4 shows a flow chart of an image display method according to another embodiment of the invention;

FIG. 5 shows a flow chart of an image display method according to another embodiment of the invention;

FIG. 6 shows a flow chart of an image display method according to another embodiment of the invention;

fig. 7 shows a flowchart of an image display method according to another embodiment of the present invention;

fig. 8 shows a flowchart of an image display method according to another embodiment of the present invention.

Detailed Description

Fig. 1 shows a schematic representation of a magnetic resonance system 100, which includes a scanner 110. The scanner 110 is used to perform a magnetic resonance scan of the subject (e.g., human body) 16 to generate image data of a region of interest of the subject 16, which may be a predetermined imaging site or imaging tissue. The image data may be a sequence of images having a plurality of images, which in one embodiment may be two-dimensional images corresponding to a plurality of slice (or slice) positions of a region of interest.

The magnetic resonance system may comprise a controller 120 coupled to the scanner 110 for controlling the scanner 110 to perform the procedure of the magnetic resonance scan described above. Specifically, the controller 120 may send a sequence control signal to relevant components of the scanner 110 (e.g., a radio frequency generator, a gradient coil driver, etc., which will be described below) through a sequencer (not shown in the figure) so that the scanner 110 performs a preset scan sequence.

It will be appreciated by those skilled in the art that the above-described "scan sequence" refers to a combination of pulses of particular amplitude, width, direction and timing, which may typically include, for example, radio frequency pulses and gradient pulses, applied when performing a magnetic resonance imaging scan. The radio frequency pulses may comprise, for example, radio frequency transmit pulses for exciting protons in the body to resonate, and the gradient pulses may comprise, for example, slice selection gradient pulses, phase encoding gradient pulses, frequency encoding gradient pulses, or the like. Typically, a plurality of scan sequences may be preset in the magnetic resonance system to enable selection of sequences that are compatible with clinical examination requirements, which may include, for example, imaging sites, imaging functions, etc.

In practice, different scan sequence types may need to be selected based on different clinical applications, such as echo-planar (EPI) sequences, gradient echo (GRE) sequences, Spin Echo (SE) sequences, Fast Spin Echo (FSE) sequences, Diffusion Weighted Imaging (DWI) sequences, Inversion Recovery (IR) sequences, and so forth, and each scan sequence may have different scan sequence parameters in different clinical applications, such as T1 weighting values, T2 weighting values, echo time, repetition time, inversion recovery time, and so forth.

In one example, the scanner 110 may include a main magnet assembly 111, a bed 112, a radio frequency generator 113, a radio frequency transmit coil 114, a gradient coil driver 115, a gradient coil assembly 116, and a data acquisition unit 117.

The main magnet assembly 111 generally comprises an annular superconducting magnet defined within an outer housing, which is mounted within an annular vacuum vessel. The annular superconducting magnet and its housing define a cylindrical space surrounding the subject 16, such as the scan volume 118 shown in fig. 1. The main magnet assembly 111 generates a constant magnetic field, the B0 field, in the Z direction of the scan bore 118. Typically, the more uniform portion of the B0 field is formed in the central region of the main magnet.

The couch 112 is adapted to carry the subject 16 and is responsive to control by the controller 120 to travel in the Z-direction to access the scanning chamber 118, for example, in one embodiment, an imaging volume of the subject 16 may be positioned to a central region of relatively uniform magnetic field strength in the scanning chamber to facilitate scanning imaging of the imaging volume of the subject 16.

The magnetic resonance system transmits a static magnetic pulse signal to the subject 16 located in the scan bore using the resulting B0 field, ordering the precession of protons of the resonance volume within the subject 16, producing a longitudinal magnetization vector.

The radio frequency generator 113 is operative to generate radio frequency pulses, e.g., radio frequency excitation pulses, responsive to control signals from the controller 120, the radio frequency excitation pulses being amplified, e.g., by a radio frequency power amplifier (not shown), and applied to the radio frequency transmit coil 114 such that the radio frequency transmit coil 114 transmits a radio frequency field B1 orthogonal to the B0 field to the subject 16 to excite nuclei within the resonating volume to generate transverse magnetization vectors.

The radio frequency transmit coil 114 may include, for example, a body coil disposed along the inner periphery of the main magnet, or a head coil dedicated to head imaging. The body coil may be connected to a transmit/receive (T/R) switch (not shown) that is controlled to switch the body coil between transmit and receive modes, in which the body coil may be used to receive magnetic resonance signals from the subject 16.

When the rf excitation pulse ends, free induction decay signals, i.e., magnetic resonance signals that can be acquired, are generated during the process of gradually returning the transverse magnetization vector of the subject 16 to zero.

The gradient coil driver 115 is operable to provide the appropriate current/power to the gradient coil assembly 116 in response to gradient pulse control signals or shim control signals issued by the controller 120.

The gradient coil assembly 116 forms a varying magnetic field in the imaging space to provide three-dimensional positional information for the magnetic resonance signals described above, on the one hand, and a compensating magnetic field for generating a B0 field to shim the B0 field, on the other hand.

The gradient coil assembly 116 may include three gradient coils for generating magnetic field gradients that are tilted into three spatial axes (e.g., X, Y, and Z axes), respectively, that are perpendicular to each other. More specifically, the gradient coil assembly 116 applies magnetic field gradients in a slice selection direction (Z-direction) for slice selection in the imaging volume. Those skilled in the art will appreciate that the slice is any one of a plurality of two-dimensional slices distributed along the Z-direction in a three-dimensional imaging volume. While scanning the imaging, the radio frequency transmit coil 114 transmits radio frequency excitation pulses to and excites the layer of the imaging volume. The gradient coil assembly 116 applies magnetic field gradients in the phase encoding direction (Y-direction) to phase encode the magnetic resonance signals of the excited layers. The gradient coil assembly 116 applies gradient fields in frequency encoding directions of the subject 16 in order to frequency encode the magnetic resonance signals of the excited slices.

The data acquisition unit 117 is configured to acquire the magnetic resonance signals (e.g., received by the body coil or the surface coil) in response to the data acquisition control signals of the controller 120, and in one embodiment, the data acquisition unit 117 may include, for example, a radio frequency preamplifier for amplifying the magnetic resonance signals, a phase detector for performing phase detection on the amplified magnetic resonance signals, and an analog/digital converter for converting the phase-detected magnetic resonance signals from analog signals to digital signals.

The magnetic resonance system 100 comprises an image reconstruction unit 130 which can reconstruct a series of two-dimensional slice images of an imaging volume of the subject 16, i.e. the image sequence described above, based on the digitized magnetic resonance signals described above. In particular, the reconstruction unit may be based on communication with the controller 120 to perform the image reconstruction described above.

The magnetic resonance system 100 comprises a processing unit 140 which may perform any required image processing on any of the images of the image sequence, such as image correction, determining display parameters of the images, etc. The image processing described above may be an improvement or adaptation of the image in any of contrast, uniformity, sharpness, brightness, etc. Specifically, the processing unit 140 may perform the above-described image processing based on communication with the controller 120.

In one embodiment, the controller 120, the image reconstruction unit 130, and the processing unit 140 may respectively or commonly include a computer and a storage medium on which a predetermined control program, a data processing program, and the like to be executed by the computer are recorded, for example, a program for implementing imaging scanning, image reconstruction, image processing, and the like may be stored, for example, a program for implementing the image display method of the embodiment of the present invention may be stored. The storage medium may include, for example, a ROM, a floppy disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, or a nonvolatile memory card.

The magnetic resonance system 100 may comprise a display unit 150 which may be used to display an operator interface as well as various data or images generated during data processing. In one aspect, the display unit 150 may display the sequential images through the display unit 150 in an arrangement manner in response to a display control signal of the controller 120, which may be generated in response to an operation of requesting reading of the images from the doctor, for example, in order of the slice positions. On the other hand, the display unit 150 may also communicate with the processing unit 140 (e.g., via the controller 120) to display the above-described sequence images according to the display parameters determined by the processing unit 140.

The processing unit 140 may specifically relate to parameters related to contrast, sharpness, brightness, uniformity, etc., such as window width values, i.e. pixel ranges of the image, and window level values, i.e. values at the center of the pixel range, as understood by a person skilled in the art, when determining display parameters of the sequence of images. It is generally desirable to set the window level value to the tissue (e.g., soft tissue, bone, blood, etc.) that best represents the lesion, and the closer the window level value is to the pixel value of that tissue, the better the uniformity of the image. And the smaller the window width value is, the higher the contrast ratio is, centered on the window position value.

The magnetic resonance system 100 includes a console 160, which may include user input devices such as a keyboard and mouse, and the controller 120 may communicate with the scanner 110, the image reconstruction unit, the processing unit 140, the display unit 150, and the like, in response to control commands generated by a user based on operating the console 160 or operating panels/keys, etc., provided on the main magnet housing.

Typically, a respective window width value and window level value is set for each image in order to expect each image in the sequence of images presented to the user to have a desired image quality, e.g. the corresponding window width value is set based on the maximum pixel value and the minimum pixel value of each image and the window level value is set based on the window width value, e.g. the window level value is the median of the window width values. In practice, however, the highlight signal of the partial image may be caused by a small amount of metal, blood vessel tissue, etc. in the human body, so that the maximum pixel value in the image is significantly too high, the window width is too wide, and the window level value obtained by the method is significantly deviated from the pixel value of the tissue to be observed, thereby causing the partial image in the image sequence to be too dark, and the brightness difference of the image sequence is large in the whole view, which brings trouble to the doctor for reading the image.

Fig. 2 shows a flowchart of an image display method according to an embodiment of the present invention, which includes steps S21, S23, and S25, as shown in fig. 2.

In step S21, a sequence of images to be displayed is acquired, the sequence of images including a plurality of images. For example, when the controller 120 receives a user request for slide reading, the processing unit 140 may be notified to retrieve a plurality of slice images generated by a magnetic resonance scan performed by the scanner 110 on the region of interest of the subject 16, or retrieve the plurality of slice images after image processing.

In step S25, the same window width value is determined for the plurality of images, and the determined window width value may be transmitted to the display unit 160 directly or through the controller 120.

In step S29, the plurality of images of the sequence of images are displayed based on the same window width value, and specifically, the display unit 160 may display pixel values outside the pixel range defined by the window width value as the background color, for example, the pixel value is "0", when the plurality of images are displayed.

By setting the same window width value for a plurality of images of the image sequence, the problems of difficult film reading, corresponding manual adjustment for different images and the like caused by overlarge brightness difference between displayed images are avoided. Setting the window level values based on the same window width value can also avoid the problem of poor uniformity among images.

Fig. 3 shows a flowchart of an image display method according to another embodiment of the present invention, which includes steps S21, S33, S35, and S29, as shown in fig. 3.

In step S33, the ordering of the pixel values of the multiple images is obtained, for example, if N pixel values are found after all the pixel values of the multiple images are counted, the N pixel values are ordered in descending or ascending order (1, 2, 3 … m-2, m-1, m, m +1, m +2 … N), where m is a natural number between 1 and N.

In step S35, the window width value is determined based on the above-mentioned sorted preset-order pixel value (e.g., mth pixel value) or a plurality of pixel values within a preset order range (e.g., mth-2 to m +2 pixel values, or q + th pixel value). Preferably, the preset sequence number may be a middle sequence number, for example, the window width value may be determined based on the pixel values arranged in the middle sequence number, or may be determined based on a plurality of pixel values arranged in a middle range (i.e., a middle sequence number range in which the middle sequence number is located).

In a specific embodiment, the pixel value of the preset signal or the middle sequence number may be directly set as the window width value, or an average value of a plurality of pixel values within the preset range or the middle sequence number range may be set as the window width value.

In the embodiment, a uniform window width value can be set for a plurality of images of an image sequence without complex operation, and the selection is carried out according to the sorting position of the pixel values instead of being determined by only depending on the maximum pixel value and the minimum pixel value, so that the problem of over-brightness or over-darkness of the images caused by over-large or over-small maximum pixel values is avoided.

Fig. 4 shows a flowchart of an image display method according to another embodiment of the present invention, which includes step S21, step S43, step S45, and step S47. Here, step S43 may be similar to step S25, e.g., determining the same window width value for the plurality of images. More specifically, step S43 may also include steps S33 and S35 to determine the same window width value for the plurality of images.

In step S45, an adjustment coefficient is determined based on one or more pieces of imaging information corresponding to the sequence of images, and the window width value is adjusted based on the adjustment coefficient. The imaging information may include, for example, one or more of an imaging region, a scan sequence, a scan plane, an echo time, an inversion recovery time, and a repetition time set when the magnetic resonance system generates the sequence image.

Those skilled in the art understand that the imaging region may include a body region of a human body, such as the head, abdomen, chest, heart, etc.; the scan planes, i.e., scan slices, correspond to two-dimensional slice images in an imaging sequence, each scan slice having a particular slice position; the echo time refers to the time range from the radio frequency excitation pulse to the center of an echo signal in a scanning sequence; the inversion time is the time range between the 180 ° inversion pulse center and the 90 ° excitation pulse center; the repetition time is the time range between the centers of two adjacent excitation pulses.

The adjustment coefficient may be determined based on a weight of one or more of the imaging information described above. The adjusting may specifically comprise multiplying the adjustment coefficient by the window width value. In a specific example, the adjustment coefficient may be less than or greater than 1.

In step S47, a plurality of images of the sequence of images are displayed based on the determined window width value, specifically, the plurality of images are displayed based on the window width value after being adjusted.

In this way, it is made possible to select an appropriate display manner for different imaging information to better meet the clinical diagnosis requirements, for example, the above adjustment coefficient may be different depending on the imaging site, since a higher image brightness may be required to make it easier to observe a lesion when reading an image of one imaging site, and a lower image brightness is required to make it easier to observe a lesion when reading an image of another imaging site. For another example, if different scanning sequences or different scanning parameters are adopted for the same imaging part, the brightness requirements during reading the film will also be different, and a proper window width value adjustment coefficient is determined by the corresponding weight to meet the corresponding requirements.

Fig. 5 shows a flowchart of an image display method according to another embodiment of the present invention, and as shown in fig. 5, the image display method according to the present embodiment includes step S21, step S43, step S55, and step S47. In step S55, one or more pieces of imaging information are input to a first deep learning network determined in advance, an adjustment coefficient is output through the first deep learning network, and the window width value determined in step S43 is adjusted based on the adjustment coefficient.

The data training may be performed by the following exemplary method to obtain the first deep learning network:

in one step, the ideal window width value adjustment coefficients of the image sequences are obtained, for example, an initial window width value may be determined for each image sequence based on any of the above embodiments, the initial window width value is manually adjusted to make the corresponding image sequence have ideal display brightness, and then the window width value adjustment coefficients corresponding to the image sequences are calculated based on the adjusted window width value and the initial window width value.

In another step, imaging information corresponding to the plurality of image sequences is determined, wherein the imaging information corresponding to each image sequence can be a single piece of information or different combinations of a plurality of pieces of information.

In another step, the window width adjustment coefficients are used as an output data set, the imaging information corresponding to the image sequences is used as an input data set, and a proper machine learning network is selected for machine learning, so that the machine learning network is endowed with network parameters related to the input data set and the output data set.

By utilizing the trained first learning network, when an image sequence is displayed, a window width value adaptive to imaging information of the image sequence can be automatically obtained, so that the display requirement of clinical diagnosis can be better met.

Fig. 6 shows a flowchart of an image display method according to another embodiment of the present invention. As shown in fig. 6, the image display method of the present embodiment includes step S21, step S43, step S65, step S66, and step S47. In step S65, user information when the sequence image is displayed is determined. In step S66, an adjustment coefficient is determined based on the determined user information, and the window width value determined in step S43 is adjusted based on the adjustment coefficient. For example, a plurality of corresponding adjustment coefficients may be determined for a plurality of user information, respectively. When the image sequence is displayed, the window width value adjusting coefficient can be automatically set based on the personalized habit or preference of the user, so that the personalized display requirement of the user can be better met.

In this embodiment, the adjustment coefficient corresponding to the user information may be stored in advance, and when the user reads the film, the user information is identified, so that the corresponding adjustment coefficient can be called to adjust the initial window width value.

Fig. 7 shows a flowchart of an image display method according to another embodiment of the present invention. As shown in fig. 7, the image display method of the present embodiment includes step S21, step S43, step S65, step S76, and step S47. In step S76, the determined user information is input into a second deep learning network determined in advance, an adjustment coefficient is output through the second deep learning network, and the window width value determined in step S43 is adjusted based on the adjustment coefficient.

The data training may be performed by the following exemplary method to obtain the second deep learning network:

in one step, a plurality of window width value adjustment coefficients for a plurality of user film-reading times can be obtained for one or more image sequences, for example, an adjusted window width value and an initial window width value before film-reading time for each user can be obtained, and a window width value adjustment coefficient corresponding to the user is calculated based on the plurality of adjusted window width values and the initial window width value.

In another step, the window width adjustment coefficients are used as an output data set, the user information of the users is used as an input data set, and a suitable machine learning network is selected for machine learning, so that the machine learning network is endowed with network parameters related to the input data set and the output data set.

By utilizing the trained second learning network, when the image sequence is displayed, the window width value adjusting coefficient can be quickly and accurately set based on the personalized habit or preference of the user.

Fig. 8 shows a flowchart of an image display method according to another embodiment of the present invention. As shown in fig. 8, the image display method of the present embodiment includes step S21, step S43, step S85, and step S47. In step S85, determining an adjustment coefficient based on one or more pieces of imaging information corresponding to the sequence of images and the current user information, and adjusting the window width value based on the adjustment coefficient, where the determined adjustment coefficient may include at least a component related to the imaging information and a component related to the user information, for example, in this step, the adjustment coefficient determined based on the imaging information and the adjustment coefficient determined based on the user information may be further mathematically operated to obtain a total adjustment coefficient, and the window width value may be adjusted by using the total adjustment coefficient; alternatively, the window width value may be adjusted based on one of the imaging information and the user information to obtain an intermediate value of the window width value, and then the intermediate value may be further adjusted based on the other of the imaging information and the user information to obtain a final window width value.

Further, in step S85, an adjustment coefficient may be obtained using a third deep learning network. For example, the current user information and imaging information are input to a third deep learning network determined in advance, an adjustment coefficient is output through the third deep learning network, and the window width value determined in step S43 is adjusted based on the adjustment coefficient.

The data training may be performed by the following exemplary method to obtain the third deep learning network:

in one step, an ideal window width value adjustment coefficient of a plurality of image sequences is obtained, for example, an initial window width value is determined for each image sequence, then adjustment coefficients for adjusting the initial window width value of the image sequence by a plurality of users are obtained, so that each image sequence has a plurality of ideal display luminances for the plurality of users, and then a plurality of window width value adjustment coefficients corresponding to each image sequence are calculated based on the adjusted window width value and the initial window width value, wherein the plurality of window width value adjustment coefficients respectively correspond to a plurality of user information.

In another step, a plurality of window width value adjustment coefficients of a plurality of image sequences are used as an output data set, imaging information and user information corresponding to the plurality of image sequences are used as input data sets, and a proper machine learning network is selected for machine learning so as to endow the machine learning network with network parameters related to the input data sets and the output data sets.

By utilizing the trained third deep learning network, when an image sequence is displayed, a window width value adjusting coefficient which can be matched with imaging information to meet the display requirement of clinical diagnosis and meet the personalized preference of a user can be obtained.

In an embodiment of the invention, the window level value is determined as the median of the window width values.

As discussed herein, deep learning techniques (also referred to as deep machine learning, hierarchical learning, deep structured learning, or the like) employ artificial neural networks for learning. Deep learning approaches feature the use of one or more network architectures to extract or model data of interest. The deep learning approach may be accomplished using one or more processing layers (e.g., input layers, output layers, convolutional layers, normalization layers, sampling layers, etc., which may have different numbers and functions of processing layers according to different deep learning network models), where the arrangement and number of layers allows the deep learning network to handle complex information extraction and modeling tasks. Certain parameters of the network (which may also be referred to as "weights" or "biases") are typically estimated by a so-called learning process (or training process). The learned or trained parameters typically result in (or output) a network corresponding to different levels of the layer, and thus different aspects of the extracted or simulated initial data or the output of a previous layer may typically represent a hierarchy or cascade of layers. Thus, the processing may be done hierarchically, i.e. an earlier or higher level layer may correspond to the extraction of "simple" features from the input data, followed by the combination of these simple features into a layer exhibiting features of higher complexity. In practice, each layer (or more specifically, each "neuron" in each layer) may employ one or more linear and/or nonlinear transformations (so-called activation functions) to process input data into an output data representation. The number of "neurons" may be constant across multiple layers, or may vary from layer to layer.

As discussed herein, a training data set having known input values (e.g., known imaging information for an image sequence, user information, etc.) and known or desired output values (e.g., known more optimal window width value adjustment coefficients) may be employed as part of an initial training of a deep learning process to solve a particular problem. In this manner, the deep learning algorithm may process the known data set or the training data set (in a supervised or guided manner or in an unsupervised or unsupervised manner) until a mathematical relationship between the initial data and the desired output is identified and/or a mathematical relationship between the inputs and outputs of each layer is identified and characterized. The learning process typically utilizes (part of) the input data and creates a network output for the input data. The created output is then compared to the expected (target) output for the data set, and the difference between the generated and expected outputs is then used to iteratively update the parameters (weights and biases) of the network. One such update/learning mechanism is to update the parameters of the network by using a random gradient descent method, although it will be understood by those skilled in the art that other methods known in the art may be used. Similarly, a separate validation data set may be employed in which both the input and the desired target values are known, but only the initial values are provided to the trained deep learning algorithm, and then the output is compared to the output of the deep learning algorithm to validate prior training and/or prevent over-training.

Based on the above description, the embodiment of the present invention may further provide a computer-readable storage medium, in which computer-readable instructions are stored, and the computer-readable instructions are used for controlling a magnetic resonance scanning system to execute the image display method of any one of the above embodiments. The computer readable storage medium may be similar to the storage medium in the controller 120 in the system shown in fig. 1.

As used herein, an element or step recited in the singular and proceeded with the word "a" or "an" should be understood as not excluding plural said elements or steps, unless such exclusion is explicitly recited. Furthermore, references to "one embodiment" of the present invention are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features. Moreover, unless explicitly stated to the contrary, embodiments "comprising," "including," "having" or "having" an element or a plurality of elements having a particular property may include additional such elements not having that property. The terms "including" and "in which" are used as plain language equivalents of the respective terms "comprising" and "characterized by". Furthermore, in the appended claims, the terms "first," "second," and "third," etc. are used merely as labels, and are not intended to impose numerical requirements or a particular positional order on their objects.

This written description uses examples to disclose the invention, including the best mode, and also to enable any person skilled in the relevant art to practice the invention, including making and using any devices or systems and performing any incorporated methods. The scope of the invention is defined by the claims and may include other examples known 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 with insubstantial differences from the literal languages of the claims.