Image recognition and selection for motion correction and peak enhancement

Abstract

A method and system for performing motion correction on imaging data. The method includes accessing a set of imaging data. The set of imaging data includes first imaging data at a first time point, second imaging data at a second time point, and third imaging data at a third time point. The location of a region of interest (ROI) is identified in the different imaging data. Differences between the locations of the ROI across the imaging data are determined and aggregated to generate an aggregate motion score for corresponding imaging data in the set of imaging data. One of the imaging data is then selected as reference imaging data for motion correction based on the aggregate motion score. Motion correction of the set of imaging data is performed based on the selected reference imaging data. Similar comparisons can be performed on images for peak enhancement of MRI imaging data.

Description

[0001] This application was filed on March 13, 2020, as a PCT international patent application and claims the benefit of U.S. patent application serial no. 62 / 818,449, filed on March 14, 2019, the disclosure of which is incorporated herein by reference in its entirety. Background Art

[0002] Medical imaging has become a widely used tool for identifying and diagnosing abnormalities in the human body, such as cancer or other conditions. For example, magnetic resonance imaging (MRI) is an imaging modality that can be used in medical applications. In MRI, three-dimensional (i.e., volumetric) imaging information of a patient's body region is acquired for diagnostic purposes. Other imaging modalities, such as computed tomography (CT), positron emission tomography (PET), mammography, and tomosynthesis, can also be used in medical imaging procedures. In some imaging modalities, images can be acquired at multiple time points, commonly referred to as dynamic imaging. For example, MRI information can be acquired at multiple time points to study the temporal progression of dynamic processes, such as blood flow. Tomosynthesis involves acquiring images of a portion of a patient (e.g., a patient's breast) at multiple angles at different time points. In some cases, contrast-enhanced or dual-energy mammography can also involve acquiring images at multiple different time points. In such dynamic imaging procedures, where images are acquired over time, the patient may move during the time required to complete the imaging procedure. If the patient moves during the imaging procedure, the acquired imaging data may need to be corrected to account for this patient movement.

[0003] It is with respect to these and other general considerations that the aspects disclosed herein are made.In addition, although relatively specific problems may be discussed, it should be understood that the examples should not be limited to solving the specific problems identified in the background or elsewhere in this disclosure. Summary of the Invention

[0004] Examples of the present disclosure describe systems and methods for improving imaging procedures and the quality of images obtained from such imaging procedures. In one aspect, the present technology relates to a method comprising accessing a set of imaging data, the set of imaging data comprising first imaging data at a first time point, second imaging data at a second time point, and third imaging data at a third time point. The method also includes identifying a first position of a region of interest (ROI) in the first imaging data; identifying a second position of the ROI in the second imaging data; and identifying a third position of the ROI in the third imaging data. The method also includes determining a plurality of differences between the identified positions, wherein the plurality of differences include differences between: the first position and the second position; the first position and the third position; and the second position and the third position. The method also includes, based on the determined plurality of differences, selecting one of the first imaging data, the second imaging data, or the third imaging data as reference imaging data for motion correction, and performing motion correction on the set of imaging data using the selected reference image.

[0005] In one example, the set of imaging data is magnetic resonance imaging (MRI) data. In another example, the set of imaging data includes a two-dimensional medical image, and the position of the ROI includes a first coordinate corresponding to a first dimension and a second coordinate corresponding to a second dimension. In yet another example, determining the difference between the first position and the second position includes: determining the difference between the first coordinate of the first position and the first coordinate of the second position; and determining the difference between the second coordinate of the first position and the second coordinate of the second position. In yet another example, the set of imaging data includes a three-dimensional medical image, and the position of the ROI includes a first coordinate corresponding to the first dimension, a second coordinate corresponding to the second dimension, and a second coordinate corresponding to the third dimension. In yet another example, determining the difference between the first position and the second position includes: determining the difference between the first coordinate of the first position and the first coordinate of the second position; determining the difference between the second coordinate of the first position and the second coordinate of the second position; and determining the difference between the third coordinate of the first position and the third coordinate of the second position. In another example, determining the difference between the first position and the second position includes determining the distance between the first position and the second position.

[0006] In another aspect, the present technology relates to a system comprising: a display; at least one processor; and a memory storing instructions that, when executed by the at least one processor, cause the system to perform a set of operations. The set of operations includes accessing a set of imaging data, the set of imaging data comprising first imaging data at a first time point, second imaging data at a second time point, and third imaging data at a third time point; identifying a first position of a region of interest (ROI) in the first imaging data; identifying a second position of the ROI in the second imaging data; and identifying a third position of the ROI in the third imaging data. The set of operations also includes determining a plurality of differences between the identified positions, wherein the plurality of differences includes differences between: a first position and a second position; a first position and a third position; and a second position and a third position. The set of operations also includes selecting one of the first imaging data, the second imaging data, or the third imaging data as reference imaging data for motion correction based on the determined plurality of differences; performing motion correction on the set of imaging data using the selected reference imaging data; and displaying at least a portion of the motion-corrected imaging data set on the display.

[0007] In an example, the system further comprises a medical imaging device, and the set of operations further comprises acquiring a set of imaging data from the medical imaging device. In another example, the medical imaging device is a magnetic resonance imaging (MRI) machine, and the imaging data comprises an MRI volume. In yet another example, the set of imaging data comprises a two-dimensional medical image, and the position of the ROI comprises a first coordinate corresponding to a first dimension and a second coordinate corresponding to a second dimension, and determining the difference between the first position and the second position comprises: determining the difference between the first coordinate of the first position and the first coordinate of the second position; and determining the difference between the second coordinate of the first position and the second coordinate of the second position. In yet another example, the medical image is a three-dimensional medical image, the position of the ROI comprises a first coordinate corresponding to the first dimension, a second coordinate corresponding to the second dimension, and a second coordinate corresponding to the third dimension, and determining the difference between the first position and the second position comprises: determining the difference between the first coordinate of the first position and the first coordinate of the second position; determining the difference between the second coordinate of the first position and the second coordinate of the second position; and determining the difference between the third coordinate of the first position and the third coordinate of the second position. In yet another example, determining the difference between the first position and the second position comprises determining a distance between the first position and the second position.

[0008] In another aspect, the present technology relates to a method that includes accessing a set of medical images acquired at multiple time points. The method also includes identifying a region of interest (ROI) in at least half of the medical images in the set of medical images; identifying a location of the ROI in at least half of the medical images in the set of medical images; comparing the identified locations of the ROI in at least one pair of medical images in the set of medical images; selecting one of the medical images in the set of medical images as a reference image for motion correction based on the comparison of the identified locations; and performing motion correction on the set of medical images using the selected reference image.

[0009] In an example, the comparison operation includes comparing the identified locations of the ROI in multiple pairs of medical images in the set of medical images. In another example, the multiple pairs of medical images include all possible pairs of medical images in the set of medical images. In yet another example, the medical images are two-dimensional medical images, and the location of the ROI includes a first coordinate corresponding to a first dimension and a second coordinate corresponding to a second dimension. In yet another example, the medical images are three-dimensional medical images, and the location of the ROI includes a first coordinate corresponding to the first dimension, a second coordinate corresponding to the second dimension, and a second coordinate corresponding to the third dimension.

[0010] In another aspect, the present technology relates to accessing a set of imaging data, the set of imaging data comprising first imaging data at a first time point, second imaging data at a second time point, and third imaging data at a third time point. The method further includes identifying a first location of a region of interest (ROI) in the first imaging data; identifying a second location of the ROI in the second imaging data; and identifying a third location of the ROI in the third imaging data. The method further includes determining a first difference between the first location and the second location; determining a second difference between the first location and the third location; and determining a third difference between the second location and the third location. The method further includes aggregating the first difference and the second difference to generate a first aggregate motion score for the first imaging data; aggregating the first difference and the third difference to generate a second aggregate motion score for the second imaging data; and aggregating the second difference and the third difference to generate a third aggregate motion score for the third imaging data. The method further includes, based on the first aggregate motion score, the second aggregate motion score, and the third aggregate motion score, selecting one of the first imaging data, the second imaging data, or the third imaging data as reference imaging data for motion correction; and performing motion correction of the set of imaging data based on the selected reference imaging data.

[0011] In an example, the first difference is the distance between the first location and the second location; the second difference is the distance between the first location and the third location; and the third difference is the distance between the second location and the third location. In another example, the first difference is the area between the first location and the second location; the second difference is the area between the first location and the third location; and the third difference is the area between the second location and the third location.

[0012] In another aspect, the present technology relates to a method comprising accessing a set of imaging data comprising first imaging data at a first time point, second imaging data at a second time point, and third imaging data at a third time point; identifying an outline of a region of interest (ROI) in the first imaging data; identifying an outline of the ROI in the second imaging data; identifying an outline of the ROI in the third imaging data; determining a first area between the first outline and the second outline; determining a second area between the first outline and the third outline; determining a third area between the second outline and the third outline; aggregating the first area and the second area to generate a first aggregate motion score for the first imaging data; aggregating the first area and the third area to generate a second aggregate motion score for the second imaging data; aggregating the second area and the third area to generate a third aggregate motion score for the third imaging data; selecting one of the first imaging data, the second imaging data, or the third imaging data as reference imaging data for motion correction based on the first aggregate motion score, the second aggregate motion score, and the third aggregate motion score; performing motion correction of the set of imaging data based on the selected reference imaging data; and displaying at least a portion of the motion-corrected imaging data set.

[0013] In an example, the first region is a non-overlapping region between a first contour and a second contour; the second region is a non-overlapping region between the first contour and a third contour; and the third region is a non-overlapping region between the second contour and the third contour. In another example, selecting one of the first imaging data, the second imaging data, or the third imaging data as reference imaging data for motion correction includes selecting imaging data with a lowest aggregate motion score. In yet another example, the first region is an overlapping region between the first contour and the second contour; the second region is an overlapping region between the first contour and the third contour; and the third region is an overlapping region between the second contour and the third contour. In yet another example, selecting one of the first imaging data, the second imaging data, or the third imaging data as reference imaging data for motion correction includes selecting imaging data with a highest aggregate motion score. In yet another example, the ROI is a skin line of a breast.

[0014] In another example, the technology relates to a method that includes accessing a set of MRI imaging data, the set of MRI imaging data including at least a first volume acquired at a first time and a second volume acquired at a second time; identifying at least one local contrast-enhanced region in the first volume; identifying at least one local contrast-enhanced region in the second volume; evaluating contrast dynamics of the local contrast-enhanced region in the first volume; evaluating contrast dynamics of the local contrast-enhanced region in the second volume; selecting the first volume or the second volume as a peak enhancement volume based on the evaluated contrast dynamics of the local contrast-enhanced region in the first volume and the second volume; and performing colorization on the set of MRI imaging data based on the peak enhancement volume.

[0015] This summary is provided to introduce in a simplified form some concepts that are further described in the following detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. Additional aspects, features, and / or advantages of the examples will be set forth in part in the following description and in part will be apparent from the description, or may be learned by practice of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Non-limiting and non-exhaustive examples are described with reference to the following figures.

[0017] Figure 1 Depicted is a set of example images acquired during a dynamic imaging procedure.

[0018] Figure 2A Depicted is another set of example images acquired during a dynamic imaging procedure.

[0019] Figure 2B The difference in the region of interest (ROI) between the two images is depicted.

[0020] Figure 2C An example of the non-overlapping area between two contours depicting the skin line of a breast.

[0021] Figure 3 Example methods for performing motion correction of medical images are described.

[0022] Figure 4 Example methods for performing motion correction of medical images are described.

[0023] Figure 5A and 5B Example methods for performing motion correction of medical images are described.

[0024] Figure 6 Depicted are example methods for performing colorization of MRI images.

[0025] Figure 7 Depicted are examples of systems for use with the medical imaging techniques discussed herein. DETAILED DESCRIPTION

[0026] Dynamic imaging is a useful tool for acquiring medical images at multiple time points. These medical images can be acquired during a single scan or imaging procedure of a patient. For example, MRI images can be acquired continuously to study the temporal progression of dynamic processes, such as blood movement. Dynamic contrast-enhanced (DCE) MRI is one such example of dynamic MRI imaging. In DCE MRI, multiple MRI volumes are acquired after intravenous injection of a contrast agent. Each acquired volume shows how the contrast agent traveled through the patient's body at the corresponding time point when the volume was acquired. Tomosynthesis involves acquiring images of a portion of a patient (e.g., a patient's breast) at multiple angles at different time points. During such dynamic imaging procedures, the patient may move during the time required to complete the imaging procedure. Patient movement is more likely with longer scan durations, and longer scans can also acquire more images than shorter scans. Each individual patient may also move differently during their individual scans. However, patient movement during any dynamic imaging procedure often reduces the final image quality of the images produced from the imaging procedure. For example, in DCE MRI, multiple images become misaligned due to patient movement, making it more difficult to visualize the dynamic process that was intended to be seen.

[0027] Therefore, it is desirable to have a process that allows images acquired during a dynamic imaging procedure to be corrected for motion. In some motion correction algorithms, motion is corrected by shifting subsequent images to match the first image. For example, in an example MRI procedure, four images may be acquired at different time points. To correct for motion during the procedure, the last three images may be shifted to align with the first image. However, this default process may result in broad correction for patient motion and may not account for different types of patient motion. Extensive motion correction on any image may degrade the resulting image quality and affect the potential clinical accuracy that can be obtained from the image, particularly when diagnosing small lesions.

[0028] The present technology improves such motion correction procedures by taking into account the specific motion of the patient being imaged and reducing the total amount of motion correction that needs to be performed on a set of medical images. For example, the present technology analyzes the position of a marker or region of interest (ROI) identified in each image acquired during a dynamic imaging procedure. As an example, the position of the ROI in a first image can be compared with the position of the ROI in each of the other acquired images. Similarly, the position of the ROI in a second image can be compared with the position of the ROI in each of the other acquired images. The comparison of the ROI positions can include determining a distance between the relative ROI positions in each of the corresponding images. Based on the comparison of the ROI positions, one of the images is then selected as a reference or base image for performing motion correction. For example, an image that will reduce the total amount of image correction for the entire image set can be selected as a reference image for motion correction. The motion correction procedure is then performed using the selected image as the reference image, which results in less overall image correction required for the dynamic imaging procedure.

[0029] The present technology is also capable of analyzing multiple images or MRI volumes to identify the volume that is most suitable for use as a peak enhancement volume for colorizing an imaged portion of a patient, such as a breast. Typically, colorization of breast MRI lesions is based on determining the contrast agent dynamics within the imaged breast tissue before and at the peak concentration of the contrast agent. In many current MRI colorization systems, a fixed timeout period, such as 120 seconds, is used to select the MRI volume. Therefore, the same volume is always used as the peak enhancement volume. For example, the volume acquired closest to the fixed timeout period is selected as the peak enhancement volume by default without any analysis of the volume itself. However, the timeout period varies between different types of MRI imaging devices, and different types of MRI imaging devices require different settings for the timeout period. This variability between imaging devices also increases the likelihood of mislabeling a volume as a peak enhancement volume, especially when considering the variability of tissue dynamics.

[0030] This technique improves the peak volume selection process by analyzing multiple MRI volumes acquired during a DCE MRI procedure. For example, the technique can evaluate the contrast dynamics of each acquired volume to more accurately select the volume that exhibits peak enhancement characteristics. This allows colorization and concentration curves for the set of MRI volumes to be based on a more accurate selection of the peak enhancement volume rather than a default time point.

[0031] Figure 1A set of example images 100 acquired during a dynamic imaging procedure is depicted. The set of images 100 includes a first image 102 acquired at a first time point, a second image 104 acquired at a second time point, a third image 106 acquired at a third time point, and a fourth image 108 acquired at a fourth time point. Each image in the set includes a depiction of a breast 110. A region of interest (ROI) 112 is also identified in each image. In the depicted example, the ROI is the centroid of the breast 110. However, the ROI may vary in other examples and may be any identifiable feature of the patient's breast or imaged portion. In examples where the breast is being imaged, the ROI may be the skin line, nipple, chest wall, or other fiducial marker. As can be seen from the set of images 100, the breast 110 and the region of interest have moved in each image. Therefore, the patient has moved between the time the first image 102 was acquired and the time the fourth image 108 was acquired, and some form of motion correction is desired.

[0032] The present technique identifies the most appropriate image in the set of images 100 to be used as a reference image for motion correction processing. For example, the reference image is an image in which the remaining references are altered to match or at least altered to move closer to the position of the breast 110 in the reference image. To select the reference image, an analysis of the position of the ROI 112 across the images is performed.

[0033] In the depicted example, the ROI 112 in the first image is located at an x-coordinate of 0 and a y-coordinate of 0. Typical coordinate notation (x, y) may be used herein. Thus, the location of the ROI 112 in the first image 102 may be referred to as (x1, y1) and have a value of (0, 0). The location of the ROI 112 in the second image 104 is represented as (x2, y2) and has a value of (3, 0). The location of the ROI 112 in the third image 106 is represented as (x3, y3) and has a value of (2, 0), and the location of the ROI 112 in the fourth image 108 is (x4, y4) and has a value of (4, 0). Thus, in the depicted example, the breast 112 is offset only in the x-direction.

[0034] To determine which image in the set of images 100 is most suitable to be selected as the reference image, the position of the ROI 112 in each image is compared with the position of the ROI 112 in the remaining images. The comparisons can be used or aggregated to determine an aggregate motion score for each image. The image in the set of images 100 having the lowest aggregate motion score can be selected as the reference image.

[0035] To determine the aggregate motion score for the first image 102, the difference between the position of the ROI 112 in the first image 102 and the position of the ROI 112 in the remaining images is determined. For example, the difference and aggregate motion score for the first image 102 are as follows:

[0036]

[0037] Table 1: First Image Analysis

[0038] As can be seen from the table above, the aggregate motion score for the first image is the sum or total of the positional differences of the ROI 112 between the first image 102 and the remaining images. Notably, in the depicted example, since the breast 110 has not moved in the Y direction, calculations for the Y coordinate are omitted, as each difference would be zero. Furthermore, the differences in this example are generally considered to be the absolute values of the differences, so that negative values can be avoided.

[0039] The difference and aggregate motion score for the second image 104 are as follows:

[0040]

[0041] Table 2: Second Image Analysis The difference and aggregate motion scores for the third image 106 are as follows:

[0042]

[0043] Table 3: Third Image Analysis

[0044] The difference and aggregate motion scores for the fourth image 108 are as follows:

[0045]

[0046] Table 4: Fourth Image Analysis

[0047] The following table provides a summary of each Total Motion Score:

[0048] Image number Total sports score First Image 9 Second image 5 Third image 5 Fourth Image 7

[0049] Table 5: Summary of Total Motion Scores for Tables 1-4

[0050] Thus, the second image 104 and the third image 106 have the lowest aggregate motion scores (5), followed by the fourth image 108 with an aggregate motion score of 7, and the first image 102 with an aggregate motion score of 9, so in this example, one of the second image 104 or the third image 108 is selected as the representative image for motion correction. In some examples, such as this example, there is a tie between two images for the lowest aggregate motion score. To break such a tie, the maximum difference between any pair can be used. For example, in this example, the calculated differences for the second image 104 are 3, 1, and 1, and the calculated differences for the third image 106 are 2, 1, and 2, so the maximum difference for the second image is 3 and the maximum difference for the third image is 2. The image with the lowest maximum difference is selected as the reference image for motion correction. Therefore, in this example, the third image 106 is selected as the reference. It is worth noting that based on the aggregate motion score, the first image 102 would be the most different choice for use as the reference image because using the first image would require the greatest amount of motion correction across the image group 100. In this way, analyzing multiple pairs of images within the image set 100 allows identification of reference images that require less motion correction than selecting an arbitrary reference image, which results in improved image quality after motion correction of the image set 100. Analyzing more or more pairs of images can also result in improved accuracy in selecting the most suitable image to use as a reference image.

[0051] FIG2 depicts another example set of images 200 acquired during a dynamic imaging procedure. The set of images 200 includes a first image 202 acquired at a first time point, a second image 204 acquired at a second time point, a third image 206 acquired at a third time point, and a fourth image 208 acquired at a fourth time point. Each image in the set includes a depiction of a breast 210. A region of interest (ROI) 212 is also identified in each image. In the depicted example, the ROI is the center of mass of the breast 210. As can be seen from the set of images 200, the breast 210 and the region of interest have moved in each image. The example depicted in FIG2 differs from the example depicted in FIG2 in that the movement of the breast 210 in FIG2 is two-dimensional.

[0052] 2 , the ROI 212 in the first image is located at (0, 0). The location of the ROI 212 in the second image 204 is (3, 1), the location of the ROI 212 in the third image 206 is (2, -2), and the location of the ROI 212 in the fourth image 208 is (-2, 1). Determining the difference between each pair of images in the image set 200 can be performed by calculating the distance to the location of the ROI 212 in each image. An example equation for calculating the distance between two ROI 212 locations is as follows:

[0053]

[0054] In the above equation, D is the distance, x1 is the x-coordinate of the first ROI 212 position, y1 is the y-coordinate of the first ROI 212 position, x2 is the x-coordinate of the second ROI 212 position, and y2 is the y-coordinate of the second ROI 212 position. It is worth noting that the above distance equation can be used to calculate Figure 1 The distances in the example in and the same results will be obtained.

[0055] Therefore, the difference and aggregate motion scores for the first image 202 are as follows:

[0056]

[0057] Table 6: First Image Analysis

[0058] The difference and aggregate motion score for the second image 204 are as follows:

[0059]

[0060] Table 7: Second Image Analysis

[0061] The difference and aggregate motion scores for the third image 206 are as follows:

[0062]

[0063] Table 8: Third Image Analysis

[0064] The difference and aggregate motion scores for the fourth image 208 are as follows:

[0065]

[0066] Table 9: Fourth Image Analysis

[0067] The following table provides a summary of each Total Motion Score:

[0068] Image number Total sports score First Image 8.22 Second image 11.32 Third image 10.98 Fourth Image 10.23

[0069] Table 10: Summary of Total Movement Scores from Tables 6-9

[0070] As can be seen from the table above, the first image 102 has the lowest aggregate motion score. Therefore, the first image 102 is selected as the reference image for motion correction.

[0071] Figure 2B The difference in ROIs in the two images is depicted. In particular, the outline of the skin line 216A of the breast 210 from image 202 is shown overlaid on the outline of the skin line 216A of the breast 210 from image 202. Figure 2A204. In some examples, the present technology can use the outline of the ROI, such as the skin line of the breast, the chest wall, or other identifiable landmark with an outline, to determine the difference between the positions of the ROI in each image. Determining the difference between the two outlines can include determining areas that are not common to the two outlines. Figure 2C An example of the area between two contours depicting the skin line of a breast. Areas that are not common or overlapping are indicated by dashed lines. The non-overlapping area can be determined for each pair of images in a set of images. The non-overlapping area can be determined by overlapping the two contours and calculating the area in the non-overlapping contours. This determination can be made through an image analysis process. The area can also be determined by representing each contour as a curve or function and then taking the integral between the difference between the two curves or functions. For example, for Figures 2B-2C , the first profile 216A can be represented by a first function f(x), and the second profile 216B can be represented by a second function g(x). The area between the two functions can be determined by taking the integral of the difference between the two functions, for example, ∫(f(x)-g(x))dx. Depending on the implementation, it may be necessary to calculate the integral between each intersection point of the two functions to determine the total area.

[0072] For each image, an aggregate motion score can also be calculated based on the sum of regional differences between each pair of images. This determination is similar to the aggregate motion score discussed above in relation to determining the distance between two points. In the example using the outline of an ROI, the aggregate motion score can be based on the area between the two outlines. The image with the lowest aggregate motion score is then selected as the reference image for performing motion correction.

[0073] It should be understood that while the example image set described above includes only four images, the process for selecting the most appropriate reference image for motion correction can be applied to image sets with a greater or lesser number of references. As an example, for each image in a set of images (regardless of the number of images), the difference between the positions of the ROI for each possible pair of images in the set can be determined. These differences can then be aggregated to determine an aggregate motion score for each image in the set. The image with the lowest aggregate motion score is then selected as the reference image for motion correction.

[0074] In addition, Figure 1 and Figure 2AIn the above example in -C, the set of images is a two-dimensional image. For example, the images may represent slices from an MRI volume. The first image may be a slice from a first MRI volume captured at a first point in time, the second image may be a slice from a second MRI volume captured at a second point in time, the third image may be a slice from a third MRI volume captured at a third point in time, and the fourth image may be a slice from a fourth MRI volume captured at a fourth point in time. When a particular image is selected as a reference image, the entire corresponding volume may be selected as a reference volume for performing motion correction. For example, if the third image is selected as the reference image, the MRI volume acquired at the third point in time may be selected as the reference volume for performing motion correction.

[0075] In other examples, the analysis and comparison of ROI locations can be performed across three-dimensional images or image data. For example, the three-dimensional location of the ROI can be identified in a first volume, and the location of the ROI can be identified in another volume. The location of the ROI can be represented by three-dimensional Cartesian coordinates (x, y, z). The location of the ROI in the first volume can then be represented as (x1, y1, z1), and the location of the ROI in the second volume can be represented as (x2, y2, z2). The distance between the two locations of the ROI can be determined using the following equation:

[0076]

[0077] As in the above example, the differences between the positions of the ROIs can be determined for all possible pairs of volumes in the volume group. The differences can be summed for each volume to determine an aggregate motion score for each volume, and the volume with the lowest aggregate motion score is selected as the reference volume for motion correction.

[0078] Furthermore, while only a single ROI is identified in the above examples, in other examples, multiple ROIs may be identified in each image. For example, a first ROI may be identified in each image, and a second ROI may be identified. The process for determining the difference between the positions of the first ROI and calculating the position difference may be as described above. The same process may then be performed for the second ROI. The aggregate motion score for each image may then be a combination of the differences determined for the first and second ROIs.

[0079] Figure 3An example method 300 for performing motion correction of medical images is depicted. In operation 302, a set of imaging data is accessed. Accessing the set of imaging data may include acquiring images from a medical imaging device and / or receiving medical images from another storage source. The set of imaging data may include first imaging data at a first time point, second imaging data at a second time point, and third imaging data at a third time point. Additional imaging dates may also be included in the set of imaging data. The set of imaging data may include, for example, MRI imaging data, such as MRI volumes and / or MRI volume slices. In operation 304, a first position of a ROI is identified in the first imaging data. Identification of the ROI in the imaging data may be performed via computer-assisted detection, which analyzes the imaging data to identify a specific ROI in the imaging data and determine its position and coordinates. In operation 306, a second position of the ROI is identified in the second imaging data, and in operation 308, a third position of the ROI is identified in the third imaging data. The second position of the ROI is the position of the ROI in the second imaging data. Similarly, the third position of the ROI is the position of the ROI in the third imaging data. In some examples, the set of imaging data includes a two-dimensional medical image, and the position of the ROI includes a first coordinate corresponding to a first dimension (e.g., the x dimension) and a second coordinate corresponding to a second dimension (e.g., the y dimension). For example, the position of the ROI can be expressed as coordinates, such as (x, y). In other examples, the set of imaging data can include a three-dimensional medical image, and the position of the ROI includes a first coordinate corresponding to the first dimension (e.g., the x dimension), a second coordinate corresponding to the second dimension (e.g., the y dimension), and a second coordinate corresponding to the third dimension (e.g., the z dimension). For example, the position of the ROI can be expressed as coordinates, such as (x, y, z). The determined difference can be a distance from one location to another location, and such a distance can be calculated or determined using the distance equation described above.

[0080] At operation 310, a plurality of differences between the identified positions of the ROI are determined. For example, a difference between (1) a first position and a second position, (2) a first position and a third position, and (3) a second position and a third position can all be determined. As an example, in a case where the set of imaging data includes a two-dimensional image, determining the difference between the first position and the second position can include determining a difference between a first coordinate of the first position and a first coordinate of the second position, and determining a difference between a second coordinate of the first position and a second coordinate of the second position. In an example where the set of imaging data includes a three-dimensional image, determining the difference between the first position and the second position can include determining a difference between a first coordinate of the first position and a first coordinate of the second position, determining a difference between a second coordinate of the first position and a second coordinate of the second position, and determining a difference between a third coordinate of the first position and a third coordinate of the second position.

[0081] Based on the multiple differences determined in operation 310, reference imaging data is selected in operation 312. For example, the first imaging data, the second imaging data, or the third imaging data is selected as reference imaging data for motion correction. The determination can be based on an aggregate motion score for each of the imaging data, and the aggregate motion score is based on the multiple differences determined. In operation 314, motion correction is performed based on the imaging data selected as reference imaging data in operation 312. For example, imaging data other than the selected imaging data can be changed to more closely match the selected imaging data. Performing motion correction can produce a set of motion-corrected imaging data. In operation 316, at least a portion of the motion-corrected set of imaging data can be displayed. The motion-corrected set of imaging data can also be stored locally or remotely. The motion-corrected set of imaging data can also be used to complete or perform a clinical task or examination, wherein an imaging procedure is performed for the clinical task or examination. The motion-corrected set of imaging data can also be used to calculate or generate a final image, such as in an MRI or tomography procedure. For example, a reconstruction of a tomosynthesis volume may be generated from a motion-corrected set of imaging data and / or a tomosynthesis slice may be generated from a motion-corrected set of imaging data.

[0082] Figure 4 Another method 400 for performing motion correction is depicted. At operation 402, a set of medical images is accessed. The set of medical images includes medical images acquired at multiple different time points. At operation 404, an ROI is identified in each medical image in the set of medical images. In some examples, the ROI may be identified in at least a majority or approximately half of the medical images in the set of medical images. At operation 406, a location of the ROI in each medical image is identified. In some examples, the location of the ROI is identified for each image in which the ROI was identified in operation 404. Identification of the ROI and identification of the ROI location may be performed using computer-assisted detection.

[0083] In operation 408, the positions of the ROIs identified in operation 406 are compared. As an example, the positions of the ROIs in at least one pair of medical images are compared. In other examples, the positions of the ROIs may be compared for multiple pairs of medical images in the set of medical images. For example, the multiple pairs may include all possible pairs of medical images in the set of medical images. In operation 410, a reference image for motion correction is selected based on the comparison of the positions of the ROIs in operation 408. In operation 412, motion correction is performed on the set of medical images based on the set of medical images. Performing motion correction may produce a set of motion-corrected medical images. In operation 414, at least a portion of the motion-corrected set of medical images may be displayed. The motion-corrected set of medical images may also be stored locally or remotely. The motion-corrected set of imaging data may also be used to complete or perform a clinical task or examination for which an imaging procedure is performed. The motion-corrected set of imaging data may also be used to calculate or generate a final image, such as in an MRI or tomography procedure. For example, a tomosynthesis volume reconstruction may be generated from the motion-corrected set of imaging data and / or a tomosynthesis slice may be generated from the motion-corrected set of imaging data.

[0084] Figure 5A Another method 500 for performing motion correction is described. At operation 502, a set of imaging data is accessed. The imaging data includes at least first imaging data at a first time point, second imaging data at a second time point, and third imaging data at a third time point. At operation 504, a first location of a ROI is identified in the first imaging data. At operation 506, a second location of the ROI is identified in the second imaging data. At operation 508, a third location of the ROI is identified in the third imaging data.

[0085] In operation 510, a first difference between a first position and a second position is determined. In operation 512, a second difference between the first position and a third position is determined. In operation 514, a third difference between the second position and the third position is determined. In operation 516, the first difference and the second difference are aggregated to generate a first aggregate motion score for the first imaging data. In operation 518, the first difference and the third difference are aggregated to generate a second aggregate motion score for the second imaging data. In operation 520, the second difference and the third difference are aggregated to generate a third aggregate motion score for the third imaging data.

[0086] In operation 522, reference imaging data is selected based on the first, second, and third composite motion scores. For example, the imaging data with the lowest aggregate motion score may be selected as the reference imaging data for motion correction. Thus, in operation 522, one of the first, second, or third imaging data is used as the reference imaging data for motion correction. In operation 524, motion correction is performed on the set of imaging data based on the selected reference imaging data. The motion-corrected imaging data may then be displayed.

[0087] Figure 5B Another method 550 for performing motion correction is depicted. At operation 552, a set of imaging data is accessed. The imaging data includes at least first imaging data at a first time point, second imaging data at a second time point, and third imaging data at a third time point. At operation 554, a first outline of a region of interest (ROI) is identified in the first imaging data. At operation 556, a second outline of the ROI is identified in the second imaging data. At operation 558, a third outline of the ROI is identified in the third imaging data.

[0088] In operation 560, a first area between a first contour and a second contour is determined. When the first imaging data and the second imaging data overlap, the determined area may be a non-overlapping area between the first contour and the second contour. In other examples, when the first imaging data and the second imaging data overlap, the determined area may be an overlapping area between the first contour and the second contour. In operation 562, a second area between the first contour and the third contour is determined. In operation 564, a third area between the second contour and the third contour is determined. In operation 566, the first area and the second area are aggregated to generate a first aggregate motion score for the first imaging data. In operation 568, the first area and the third area are aggregated to generate a second aggregate motion score for the second imaging data. In operation 570, the second area and the third area are aggregated to generate a third aggregate motion score for the third imaging data.

[0089] In operation 572, reference imaging data is selected based on the first composite motion score, the second composite motion score, and the third composite motion score. For example, in an example where the regions determined in operations 560 to 564 are non-overlapping regions of the corresponding contours, the imaging data with the lowest aggregate motion score can be selected as the reference imaging data for motion correction. In an example where the regions determined in operations 560 to 564 are overlapping regions of the corresponding contours, the imaging data with the highest aggregate motion score can be selected as the reference imaging data for motion correction. Therefore, in operation 572, one of the first imaging data, the second imaging data, or the third imaging data is used as the reference imaging data for motion correction. In operation 574, motion correction is performed on the set of imaging data based on the selected reference imaging data. The motion-corrected imaging data can then be displayed. The motion-corrected set of imaging data can also be used to complete or perform a clinical task or examination for which an imaging procedure is performed. The motion-corrected set of imaging data can also be used to calculate or generate a final image, such as in an MRI or tomography procedure. For example, a reconstruction of a tomosynthesis volume may be generated from a motion-corrected set of imaging data and / or a tomosynthesis slice may be generated from a motion-corrected set of imaging data.

[0090] Figure 6 An example method for performing colorization of an MRI image is described. At operation 602, a set of MRI imaging data is accessed. The set of MRI imaging data may include at least a first volume acquired at a first time and a second volume acquired at a second time. Additional volumes may also be included in the set of MRI imaging data. At operation 604, at least one local contrast-enhanced region is identified in at least two MRI images in the set of MRI imaging data. For example, the local contrast-enhanced region may be identified in the first volume and the second volume. At operation 606, for the MRI volume in which the local contrast-enhanced region is identified, the contrast dynamics of the identified local contrast-enhanced region is evaluated. Evaluating the identified local contrast-enhanced region of each MRI volume may include performing colorization of each MRI volume by treating each MRI volume as if it were a peak-enhanced volume. For example, colorization of the first MRI volume may be performed, treating the first MRI volume as a peak-enhanced volume, and the contrast dynamics of the identified local contrast-enhanced region may be evaluated. The same operation may be performed for the second MRI volume.

[0091] At operation 608, a peak enhancement volume is selected based on the estimated contrast dynamics of the local contrast enhancement region. For example, selecting the peak enhancement volume may include comparing the estimated contrast dynamics of the local contrast enhancement region for each MRI volume in the set of MRI imaging data. At operation 610, colorization of the set of MRI imaging data is performed based on the peak enhancement volume selected in operation 608. The colorized MRI imaging data set may then be displayed and / or stored locally or remotely.

[0092] Figure 7 An example of a system 700 is shown having a medical imaging device 701 and a suitable operating environment 703, in which one or more of the present examples of medical imaging can be implemented. The medical imaging device 701 can be any medical imaging device capable of dynamic imaging, such as an MRI device. The medical imaging device 701 can communicate with the operating environment 703 and be configured to transmit medical images to the operating environment 703. The medical imaging device 701 can also communicate with a remote storage device 705 and be configured to transmit medical images to the remote storage device 705. The remote storage device 705 can also communicate with the operating environment 703 and be configured to send stored medical images to the environment 703.

[0093] The operating environment 703 can be incorporated directly into the medical imaging device 701, or can be incorporated into a computer system that is separate from the imaging system herein but is used to control the imaging system herein. This is merely one example of a suitable operating environment and is not intended to limit the scope of use or functionality. Other computing systems, environments, and / or configurations that may be suitable for use include, but are not limited to, imaging systems, personal computers, server computers, handheld or laptop devices, multiprocessor systems, microprocessor-based systems, programmable consumer electronics such as smartphones, network PCs, minicomputers, mainframe computers, tablet computers, and distributed computing environments that include any of the above systems or devices.

[0094] In its most basic configuration, the operating environment 703 typically includes at least one processor 702 and memory 704. Depending on the exact configuration and type of computing device, the memory 704 (which stores instructions for executing the image acquisition and processing methods disclosed herein) may be volatile (such as RAM), non-volatile (such as ROM, flash memory, etc.), or some combination of the two. Figure 7706. Furthermore, the environment 703 may also include storage devices (removable 708 and / or non-removable 710), including but not limited to magnetic or optical disks, solid-state devices, or tape. Similarly, the environment 703 may also have one or more input devices 714, such as a touch screen, keyboard, mouse, pen, or voice input, and / or one or more output devices 716, such as a display, speaker, or printer. The environment may also include one or more communication connections 712, such as LAN, WAN, point-to-point, Bluetooth, RF, or the like.

[0095] The operating environment 703 typically includes at least some form of computer-readable media. Computer-readable media can be any available media that can be accessed by the processing unit 702 or other device that includes the operating environment. As an example, the operating environment can include at least one processor 702 and a memory 704 operatively connected to the at least one processor 702. The memory stores instructions that, when executed by the at least one processor, cause the system to perform a set of operations, such as the operations described herein, including the method operations discussed above.

[0096] By way of example, and not limitation, computer-readable media may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented using any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVDs) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, solid-state storage, or any other tangible medium that can be used to store the desired information. Communication media embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and include any information transmission medium. The term "modulated data signal" refers to a signal that has one or more characteristics set or changed in such a way as to encode information in the signal. By way of example, and not limitation, communication media include wired media such as a wired network or direct wired connection, as well as wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable media. A computer-readable device is a hardware device that incorporates computer storage media.

[0097] Operating environment 703 can be a single computer that is connected to the logic of one or more remote computers and operates in a networked environment. The remote computer can be a personal computer, server, router, network PC, peer device or other common network node, and usually includes many or all of the above elements and other elements not mentioned in this way. The logical connection can include any method supported by available communication media. Such a network environment can be used in offices, enterprise-wide computer networks, intranets and the Internet.

[0098] In some embodiments, the components described herein include such modules or instructions that can be executed by the computer system 703, which can be stored on computer storage media and other tangible media and transmitted in communication media. Computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Any combination of the above should also be included in the scope of computer-readable media. In some embodiments, the computer system 703 is part of a network that stores data in remote storage media for use by the computer system 703.

[0099] The embodiments described herein can be adopted using software, hardware, or a combination of software and hardware to implement and execute the systems and methods disclosed herein. Although specific devices have been described as performing specific functions throughout the disclosure, it will be understood by those skilled in the art that these devices are provided for illustrative purposes and that other devices can be adopted to perform the functions disclosed herein without departing from the scope of this disclosure. In addition, some aspects of the disclosure have been described above with reference to block diagrams and / or operational diagrams of systems and methods according to aspects of the disclosure. The functions, operations, and / or actions marked in the boxes may not occur in the order shown in any corresponding flow chart. For example, depending on the functions and implementations involved, two boxes shown in succession may actually be executed or performed substantially simultaneously or in reverse order.

[0100] This disclosure describes some embodiments of the present technology with reference to the accompanying drawings, of which only some of the possible embodiments are shown. However, other aspects can be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to make this disclosure thorough and complete, and to fully convey the scope of possible embodiments to those skilled in the art. In addition, as used herein and in the claims, the phrase "at least one of element A, element B, or element C" is intended to express any one of the following: element A, element B, element C, element A and element B, element A and element C, element B and element C, element A, B, C. In addition, those skilled in the art will understand that terms such as "approximately" or "substantially" are conveyed according to the measurement techniques used herein. To the extent that those skilled in the art may not clearly define or understand such terms, the term "approximately" should refer to plus or minus ten percent.

[0101] Although specific embodiments are described herein, the scope of the present technology is not limited to those specific embodiments. In addition, although different examples and embodiments may be described separately, such embodiments and examples may be combined with each other when implementing the technology described herein. Those skilled in the art will recognize other embodiments or improvements within the scope and spirit of the present technology. Therefore, specific structures, actions, or media are disclosed only as illustrative examples. The scope of the present technology is defined by the appended claims and any equivalents thereof.

Claims

1. A method for performing motion correction, comprising: accessing a set of imaging data, the set of imaging data comprising first imaging data at a first time point, second imaging data at a second time point, and third imaging data at a third time point; identifying a first location of a region of interest (ROI) in the first imaging data; identifying a second location of the ROI in the second imaging data; identifying a third position of the ROI in the third imaging data; A plurality of differences between the identified locations is determined, wherein the plurality of differences includes differences between: first position and second position; First and third positions; as well as Second and third positions; selecting one of the first imaging data, the second imaging data, or the third imaging data as reference imaging data for motion correction based on the determined plurality of differences such that an overall amount of image correction of the set of imaging data is reduced; as well as Motion correction is performed on the set of imaging data using the selected reference imaging data.

2. The method of claim 1, wherein the set of imaging data is magnetic resonance imaging (MRI) data. 3 . The method according to claim 1 , wherein the set of imaging data comprises a two-dimensional medical image, and the position of the ROI comprises a first coordinate corresponding to a first dimension and a second coordinate corresponding to a second dimension.

4. The method of claim 3 , wherein determining the difference between the first position and the second position comprises: determining a difference between a first coordinate of the first location and a first coordinate of the second location; as well as A difference between the second coordinate of the first location and the second coordinate of the second location is determined.

5. The method of any one of claims 1-2, wherein the set of imaging data comprises a three-dimensional medical image, and the position of the ROI comprises a first coordinate corresponding to a first dimension, a second coordinate corresponding to a second dimension, and a third coordinate corresponding to a third dimension.

6. The method of claim 5, wherein determining the difference between the first position and the second position comprises: determining a difference between a first coordinate of the first location and a first coordinate of the second location; determining a difference between a second coordinate of the first location and a second coordinate of the second location; as well as A difference between the third coordinate of the first location and the third coordinate of the second location is determined.

7. The method of any one of claims 1-2, wherein determining the difference between the first position and the second position comprises determining a distance between the first position and the second position.

8. A system for performing motion correction, comprising: monitor; at least one processor; as well as a memory storing instructions that, when executed by at least one processor, cause the system to perform a set of operations comprising: accessing a set of imaging data, the set of imaging data comprising first imaging data at a first point in time, second imaging data at a second point in time, and third imaging data at a third point in time; identifying a first location of a region of interest (ROI) in the first imaging data; identifying a second location of the ROI in the second imaging data; identifying a third position of the ROI in the third imaging data; determining a plurality of differences between the identified locations, The differences include the following: first position and second position; First position and third position; and Second and third positions; selecting one of the first imaging data, the second imaging data, or the third imaging data as reference imaging data for motion correction based on the determined plurality of differences such that an overall amount of image correction of the set of imaging data is reduced; performing motion correction on the set of imaging data using the selected reference imaging data; and An image based on the motion-corrected set of imaging data is displayed on a display.

9. The system of claim 8, further comprising a medical imaging device, and the set of operations further comprises acquiring the set of imaging data from the medical imaging device.

10. The system according to claim 9, wherein: The medical imaging device is a magnetic resonance imaging (MRI) machine, and the imaging data comprises an MRI volume.

11. The system according to any one of claims 8 to 10, wherein: The set of imaging data includes a two-dimensional medical image, and the position of the ROI includes a first coordinate corresponding to a first dimension and a second coordinate corresponding to a second dimension, and wherein determining a difference between the first position and the second position includes: determining a difference between the first coordinate of the first location and the first coordinate of the second location; and A difference between the second coordinate of the first location and the second coordinate of the second location is determined.

12. The system according to any one of claims 8 to 10, wherein: The medical image is a three-dimensional medical image, and the position of the ROI includes a first coordinate corresponding to a first dimension, a second coordinate corresponding to a second dimension, and a third coordinate corresponding to a third dimension, and determining a difference between the first position and the second position includes: determining a difference between a first coordinate of the first location and a first coordinate of the second location; determining a difference between the second coordinate of the first location and the second coordinate of the second location; and A difference between the third coordinate of the first location and the third coordinate of the second location is determined.

13. The system of any one of claims 8-10, further comprising wherein determining the difference between the first position and the second position comprises determining a distance between the first position and the second position.

14. A method for performing motion correction, comprising: Access to a set of medical images acquired at multiple time points; identifying a region of interest (ROI) in at least half of the medical images in the set of medical images; identifying a location of the ROI in at least half of the medical images in the set of medical images; comparing the identified locations of the ROI in at least one pair of medical images in the set of medical images; selecting one of the medical images in the set of medical images as a reference image for motion correction based on the comparison of the identified locations such that an amount of image correction of the set of medical images is reduced; as well as Motion correction is performed on the set of medical images using the selected reference image.

15. The method of claim 14, wherein the comparing operation comprises comparing the identified locations of the ROI in pairs of medical images in the set of medical images.

16. The method according to claim 15, wherein The plurality of pairs of medical images include all possible pairs of medical images in the set of medical images.

17. The method according to claim 14, wherein: The medical image is a two-dimensional medical image, and the position of the ROI includes a first coordinate corresponding to a first dimension and a second coordinate corresponding to a second dimension.

18. The method according to claim 14, wherein The medical image is a three-dimensional medical image, and the position of the ROI includes a first coordinate corresponding to a first dimension, a second coordinate corresponding to a second dimension, and a third coordinate corresponding to a third dimension.

19. A method for performing motion correction, comprising: accessing a set of imaging data, the set of imaging data comprising first imaging data at a first point in time, second imaging data at a second point in time, and third imaging data at a third point in time; identifying a first location of a region of interest (ROI) in the first imaging data; identifying a second location of the ROI in the second imaging data; identifying a third position of the ROI in the third imaging data; determining a first difference between the first position and the second position; determining a second difference between the first position and the third position; determining a third difference between the second position and the third position; aggregating the first difference and the second difference to generate a first aggregate motion score for the first imaging data; aggregating the first difference and the third difference to generate a second aggregate motion score for the second imaging data; aggregating the second difference and the third difference to generate a third aggregate motion score for third imaging data; selecting, based on the first aggregate motion score, the second aggregate motion score, and the third aggregate motion score, imaging data having a lowest aggregate motion score among the first imaging data, the second imaging data, or the third imaging data as reference imaging data for motion correction; as well as Motion correction of the set of imaging data is performed based on the selected reference imaging data.

20. The method of claim 19, wherein: The first difference is the distance between the first position and the second position; The second difference is the distance between the first position and the third position; as well as The third difference is the distance between the second position and the third position.

21. The method according to any one of claims 19-20, wherein: The first difference is the area between the first location and the second location; The second difference is the area between the first position and the third position; as well as The third difference is the area between the second position and the third position.

22. A method for performing motion correction, comprising: accessing a set of imaging data, the set of imaging data comprising first imaging data at a first point in time, second imaging data at a second point in time, and third imaging data at a third point in time; identifying an outline of a region of interest (ROI) in the first imaging data; identifying an outline of the ROI in the second imaging data; identifying an outline of the ROI in the third imaging data; determining a first area between the first contour and the second contour; determining a second area between the first contour and the third contour; determining a third region between the second contour and the third contour; aggregating the first region and the second region to generate a first aggregate motion score for the first imaging data; aggregating the first region and the third region to generate a second aggregate motion score for second imaging data; aggregating the second region and the third region to generate a third aggregate motion score for third imaging data; selecting, based on the first aggregate motion score, the second aggregate motion score, and the third aggregate motion score, imaging data having a lowest aggregate motion score among the first imaging data, the second imaging data, or the third imaging data as reference imaging data for motion correction; performing motion correction of the set of imaging data based on the selected reference imaging data; as well as At least a portion of the motion-corrected set of imaging data is displayed.

23. The method of claim 22, wherein: The first region is a non-overlapping region between the first contour and the second contour; The second area is a non-overlapping area between the first outline and the third outline; and The third area is a non-overlapping area between the second outline and the third outline.

24. The method according to claim 23, wherein Selecting one of the first imaging data, the second imaging data, or the third imaging data as reference imaging data for motion correction includes selecting imaging data having a lowest aggregate motion score.

25. The method of claim 22, wherein: The first area is the overlapping area between the first outline and the second outline; The second area is an overlapping area between the first outline and the third outline; and The third area is an overlapping area between the second outline and the third outline.

26. The method according to claim 25, wherein Selecting one of the first imaging data, the second imaging data, or the third imaging data as reference imaging data for motion correction includes selecting imaging data having a highest aggregate motion score.

27. The method according to any one of claims 22 to 26, wherein: The ROI is the skin line of the breast.

28. A method for performing motion correction, comprising: accessing a set of MRI imaging data, the set of MRI imaging data comprising at least a first volume acquired at a first time and a second volume acquired at a second time; identifying at least one local contrast-enhanced region in the first volume; identifying the at least one local contrast-enhanced region in the second volume; evaluating contrast dynamics of a localized contrast-enhanced region in the first volume; evaluating contrast dynamics of the localized contrast-enhanced region in the second volume; selecting a volume of the first volume or the second volume showing a peak enhancement characteristic as a peak enhancement volume based on the assessed contrast dynamics of the local contrast enhancement regions in the first volume and the second volume; as well as Colorization is performed on the set of MRI imaging data based on a peak enhancement volume.

Images