Contrast enhanced breast imaging system and method

Abstract

Methods and systems for contrast enhanced breast imaging are provided. A method includes automatically distinguishing a first region of interest (ROI) corresponding to breast parenchyma enhancement (BPE) in a contrast-enhanced breast image. The method further includes automatically adjusting an appearance of the first ROI, generating an adjusted BPE image, and displaying the adjusted BPE image and the contrast-enhanced breast image at a display.

Description

Technical Field

[0001] Embodiments of the subject matter disclosed herein relate to systems and methods for contrast-enhanced breast imaging. Background Art

[0002] Contrast-enhanced imaging is a screening / diagnostic method that can be used to visualize lesions in tissue such as breast tissue. Contrast-enhancing agents are administered intravenously and may localize in lesion tissue due to rapid neovascularization around the lesion, resulting in imperfect blood vessels that may leak contrast agent into surrounding tissue. Contrast enhancement is particularly useful in imaging lesions in breasts with dense breast tissue. Contrast-enhancing agents may additionally be delivered to normal, healthy breast tissue and appear in contrast-enhanced images as areas of enhanced contrast in a phenomenon known as breast background parenchymal enhancement. Summary of the invention

[0003] In one embodiment, a method includes: automatically distinguishing a first region of interest (ROI) of a contrast-enhanced breast image, wherein the first ROI corresponds to background parenchymal enhancement (BPE); automatically adjusting an appearance of the first ROI and generating an adjusted BPE image; and displaying the contrast-enhanced breast image and the adjusted BPE image at a display.

[0004] It should be understood that the above brief description is provided to introduce in a simplified form selected concepts that are further described in the detailed description. It is not meant to identify key features or essential features of the claimed subject matter, the scope of which is uniquely defined 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 part of this disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] The present invention will be better understood by reading the following description of non-limiting embodiments with reference to the accompanying drawings, in which:

[0006] Figure 1 is a schematic diagram of a digital mammography system according to one embodiment;

[0007] Figure 2 Contrast-enhanced mammography (CEM) images showing background parenchymal enhancement (BPE);

[0008] Figure 3 is a flow chart of a method for displaying a BPE-free image according to one embodiment;

[0009] Figure 4 CEM images showing lesions and BPE;

[0010] Figure 5For those without BPE Figure 4 images;

[0011] Figure 6 The first example of a display showing low-energy, reconstructed, and BPE-free images;

[0012] Figure 7 A second example of a display showing a low energy, reconstituted and BPE-free image;

[0013] Figure 8 A third example of a display showing a low energy, reconstituted and BPE-free image;

[0014] Fig. 9 is a block diagram of an exemplary embodiment of an image processing system; and

[0015] Fig.10 A block diagram of an exemplary embodiment of a method for identifying and displaying BPE regions and suspicious regions of a contrast-enhanced breast image. DETAILED DESCRIPTION

[0016] The following description relates to systems and methods for displaying contrast-enhanced breast images. The contrast-enhanced breast images may be contrast-enhanced digital mammography (CEM) images or contrast-enhanced breast magnetic resonance imaging (MRI) images or contrast-enhanced breast computed tomography (CT). In CEM and contrast-enhanced breast MRI and contrast-enhanced breast CT, contrast agents are administered intravenously and preferentially localize in lesions or other suspicious areas due to leaky neovascularization surrounding the lesions. Background parenchymal enhancement (BPE) may also occur during a CEM or contrast-enhanced MRI procedure or a contrast-enhanced CT procedure, where contrast agents are also localized in normal, healthy breast tissue. Clinicians reviewing CEM or contrast-enhanced breast MRI or contrast-enhanced breast CT images may seek to distinguish lesions from BPE. Methods and systems for automatically adjusting contrast BPE in contrast-enhanced breast images can help clinicians quickly and accurately identify whether a lesion is present in a contrast-enhanced breast image in addition to accurately defining the location of the lesion (if any) within the image. Alternatively, the presence or absence of BPE may also be information used by clinicians to aid in diagnosis and cancer risk estimation, and increased contrast of BPE may be desirable.

[0017] A block diagram of an imaging processing system that may store one or more methods for identifying and displaying CEM and / or contrast-enhanced breast MRI images and / or contrast-enhanced breast CT is shown in FIG. Fig. 9 The image processing system can be communicatively coupled to an imaging system, which can be an MRI system or a digital mammography system or a breast CT system. A schematic diagram of a digital mammography system is shown in Figure 1A digital mammography system can be used to acquire CEM images that can be automatically processed and displayed by methods for automatically distinguishing BPE from suspicious areas and adjusting the BPE displayed in the image. The BPE adjustment and display system and method can also be applied to any contrast-enhanced breast image, such as those obtained by contrast-enhanced breast MRI or by contrast-enhanced breast CT. An example of a CEM image including BPE is shown in Figure 2 BPE can make it difficult for clinicians to correctly distinguish any lesions (if present) from healthy tissue. Clinicians can use diagnostic tools such as Figure 3 The method shown in FIG. 1 is a method for automatically adjusting the BPE of a contrast-enhanced breast image. As a first step, the method can automatically distinguish BPE contrast enhancement from suspicious area contrast enhancement. An example of a CEM image with a region of interest (ROI) that is distinguished as BPE or suspicious area is shown in FIG. Figure 4 After differentiating the lesion area and the BPE area in the contrast-enhanced image and adjusting the image, a BPE-free image can be displayed to the clinician. Figure 4 The image is shown in Figure 5 In the present invention, the contrast of the BPE area is adjusted to form a BPE-free image. The BPE-free image herein may refer to an image in which the contrast in the area determined to be BPE is adjusted to the background level. An algorithm may be used to distinguish between BPE and suspicious areas and adjust the display of BPE in the image. Fig.10 Shows the use of executable Figure 3 An example of a block diagram of an algorithm of some of the steps of the method is shown. Figure 3 The method can output images for review by a clinician. When reviewing the images, the clinician can review low energy images (for CEM) or other images in which contrast media does not affect the contrast of the image, reconstructed images showing all contrast enhancements in addition to no BPE and / or reduced BPE images. Depending on the clinician's preference, display size and / or image complexity, and other factors, multiple display options may be desired. As a first example, the low energy, reconstructed, and no BPE images may be displayed as shown in FIG. Figure 6 As a second example, a clinician may view a single image at a time that gradually transitions between low energy, reconstructed, and BPE-free images, such as Figure 7 As a third example, the clinician may scroll between low energy images, reconstructed images, and images with BPE adjusted at different levels, such as Figure 8 shown.

[0018] First go to Fig. 9, which shows an image processing system 900 according to an exemplary embodiment. In some embodiments, the image processing system 900 is incorporated into an imaging system such as a medical imaging system. In some embodiments, at least a portion of the image processing system 900 is disposed at a device (e.g., an edge device, a server, etc.) that is communicatively connected to the medical imaging system via a wired connection and / or a wireless connection. In some embodiments, at least a portion of the image processing system 900 is disposed at a device (e.g., a workstation) located away from the medical imaging system, which is configured to be able to receive images from the medical imaging system or from a storage device configured to store images acquired by the medical imaging system. The image processing system 900 may include an image processing device 902, a user input device 930, and a display device 920. In some embodiments, the image processing device 902 may be communicatively connected to a picture archiving and communication system (PACS), and may receive images from the PACS and / or send images to the PACS.

[0019] Image processing device 902 includes processor 904, which is configured to execute machine-readable instructions stored in non-transitory memory 906. Processor 904 can be a single-core processor or a multi-core processor, and the program executed thereon can be configured for parallel processing or distributed processing. In some embodiments, processor 904 can optionally include separate components spread over two or more devices, which can be remotely located and / or configured for collaborative processing. In some embodiments, one or more aspects of processor 904 can be virtualized and performed by a remotely accessible networked computing device configured in a cloud computing configuration.

[0020] The non-transitory memory 906 may store a BPE algorithm 908, a suspicious region algorithm 912, and an adjustment algorithm 914, which may be used to perform the following description with respect to Figure 3 In some examples, the BPE algorithm 908 and the suspicious region algorithm 912 may be combined into a single BPE and suspicious region algorithm 916. In an alternative embodiment, the BPE algorithm 908, the suspicious region algorithm 912, and the adjustment algorithm 914 may be combined into a single identification / adjustment algorithm 918. The details of the BPE algorithm 908, the suspicious region algorithm 912, and the adjustment algorithm 914 may be described below with respect to Fig.10 Further discussion.

[0021] In some embodiments, non-transitory memory 906 may include components disposed at two or more devices that may be remotely located and / or configured for collaborative processing. In some embodiments, one or more aspects of non-transitory memory 906 may include a remotely accessible networked storage device configured in a cloud computing configuration.

[0022] The image processing system 900 may also include a user input device 930. The user input device 930 may include one or more of a touch screen, a keyboard, a mouse, a trackpad, a motion sensing camera, or other devices configured to enable a user to interact with and manipulate data within the image processing system 900. In some embodiments, the user input device 930 enables a user to select one or more types of ROIs to be segmented in a medical image.

[0023] The display device 920 may include one or more display devices utilizing almost any type of technology. In some embodiments, the display device 920 may include a computer monitor, a touch screen, a projector, or other display devices known in the art. The display device 920 may be configured to receive data from the image processing device 902 and display a contrast-enhanced breast image that is modified to hide or highlight suspicious areas of the BPE and the image. In some embodiments, the image processing device 902 may determine a standard view classification of a medical image, may select a graphical user interface (GUI) based on the standard view classification of the image, and may display the medical image and the GUI via the display device 920. The display device 920 may be combined with the processor 904, the non-transitory memory 906, and / or the user input device 930 in a shared housing, or may be a peripheral display device, and may include a monitor, a touch screen, a projector, or other display devices known in the art that enable a user to view images, and / or interact with various data stored in the non-transitory memory 906.

[0024] Understandably, Fig. 9 The image processing system 900 shown is for illustration and not for limitation. Another suitable image processing system may include more, fewer, or different components.

[0025] Now go to Figure 1 , shows a digital mammography system 100 including an x-ray system 10 for performing a mammography procedure according to an embodiment of the present disclosure. The digital mammography system 100 may be an example of an imaging processing device, such as the one described above with respect to Fig. 9 The image processing device 902 is described. In some examples, the x-ray system 10 can be a tomosynthesis system, such as a digital breast tomosynthesis (DBT) system. In addition, the x-ray system 10 can be used to perform one or more procedures, including digital tomosynthesis imaging and DBT-guided breast biopsy.

[0026] The x-ray system 10 includes a support structure 42 to which a radiation source 16, a radiation detector 18, and a collimator 20 are attached. The radiation source 16 is housed within a gantry 15 that is movably coupled to the support structure 42. Specifically, the gantry 15 may be mounted to the support structure 42 so that the gantry 15 including the radiation source 16 may rotate relative to the radiation detector 18 about an axis 58. The rotation angle range of the gantry 15 housing the radiation source 16 indicates rotation up to a desired angle in either direction about the axis 58. For example, the rotation angle range of the radiation source 16 may be -θ to +θ, where θ may make the angle range a limited angle range of less than 360 degrees. An exemplary x-ray system may have an angle range of ±11 degrees, which may allow the gantry to rotate from -11 degrees to +11 degrees (i.e., rotation of the radiation source) about the axis of rotation of the gantry. The angle range may vary according to manufacturing specifications. For example, the angle range of a DBT system may be approximately ±11 degrees to ±60 degrees, depending on manufacturing specifications.

[0027] The radiation source 16 is oriented toward the volume or object to be imaged and is configured to emit radiation rays at desired times to acquire one or more images. The radiation detector 18 is configured to receive the radiation rays via the surface 24. The detector 18 may be any of a variety of different detectors, such as an x-ray detector, a digital radiography detector, or a flat panel detector. The collimator 20 is disposed adjacent to the radiation source 16 and is configured to adjust the irradiation area of ​​the subject.

[0028] In some embodiments, the system 10 may also include a patient shield 36 mounted to the radiation source 16 via a mask rail 38 so that a body part of the patient (e.g., head) is not directly exposed to radiation. The system 10 may also include a compression paddle 40 that may be capable of moving upward and downward relative to the support structure along a vertical axis 60. Thus, the compression paddle 40 may be adjusted to be positioned closer to the radiation detector 18 by moving the compression paddle 40 downward toward the detector 18, and the distance between the detector 18 and the compression paddle 40 may be increased by moving the compression paddle upward away from the detector along the vertical axis 60. The movement of the compression paddle 40 may be adjusted by a user via a compression paddle actuator (not shown) included in the x-ray system 10. The compression paddle 40 may hold a body part (such as a breast) in position against the surface 24 of the radiation detector 18. The compression paddle 40 may compress the body part and hold the body part in position while optionally providing a hole to allow insertion of a biopsy needle, such as a core needle or a vacuum-assisted core needle. Thus, compression paddles 40 may be used to compress a body part to minimize the thickness through which x-rays pass and to help reduce movement of the body part due to patient movement. X-ray system 10 may also include a subject support (not shown) on which a body part may be positioned.

[0029] The digital mammography system 100 may also include a workstation 43 including a controller 44 and a memory, the controller including at least one processor. The controller 44 may be communicatively coupled to one or more components of the x-ray system 10, including one or more of the radiation source 16, the radiation detector 18, the compression paddle 40, and the biopsy device. In one embodiment, communication between the controller and the x-ray system 10 may be via a wireless communication system. In other embodiments, the controller 44 may be in electrical communication with one or more components of the x-ray system via a cable 47. Furthermore, in an exemplary embodiment, as shown in FIG. Figure 1 As shown, the controller 44 is integrated into the workstation 43. In other embodiments, the controller 44 may be integrated into one or more of the various components of the system 10 disclosed above. In addition, the controller 44 may include processing circuitry that executes stored program logic, and may be any of a variety of computers, processors, controllers, or combinations thereof that are usable and compatible with various types of equipment and devices used in the x-ray system 10.

[0030] Workstation 43 may include a radiation shield 48 that protects an operator of system 10 from radiation rays emitted by radiation source 16. Workstation 43 may also include a display 50, keyboard 52, mouse 54, and / or other suitable user input devices that facilitate control of system 10 via user interface 56.

[0031] The controller 44 may regulate the operation and functionality of the x-ray system 10. For example, the controller 44 may provide timing control regarding when the x-ray source 16 emits x-rays, and may further regulate how the detector 18 reads and transmits information or signals after the x-rays strike the detector 18, as well as how the x-ray source 16 and detector 18 move relative to each other and relative to the body part being imaged. The controller 44 may also control the manner in which information, including images 42 and data acquired during operation, is processed, displayed, stored, and manipulated. The operations performed by the controller 44 as described herein are described herein. Figure 2 and Figure 3 The various processing steps described may be provided by a set of instructions stored in a non-volatile memory of the controller 44 .

[0032] Further, as described above, the radiation detector 18 receives radiation rays emitted by the radiation source 16. Specifically, during imaging with the x-ray system, a projection image of the imaged body part can be obtained at the detector 18. In some embodiments, data received by the radiation detector 18, such as projection image data, can be communicated electronically and / or wirelessly from the radiation detector 18 to the controller 44. The controller 44 can then reconstruct one or more scanned images based on the projection image data, for example by implementing a reconstruction algorithm. The reconstructed image can be displayed to the user on the user interface 56 via the display 50 (e.g., a display screen).

[0033] The radiation source 16 together with the radiation detector 18 form part of the x-ray system 10, which provides x-ray images for the purpose of screening for abnormalities, diagnosis, dynamic imaging and image-guided biopsy. For example, the x-ray system 10 can be operated in a mammography mode to screen for abnormalities. During mammography, the patient's breast is positioned and compressed between the detector 18 and the compression paddle 40. Therefore, the volume of the x-ray system 10 between the compression paddle 40 and the detector 18 is the imaging volume. The radiation source 16 then emits radiation rays onto the compressed breast, and a projection image of the breast is formed on the detector 18. The projection image can then be reconstructed by the controller 44 and displayed on the interface 50. During mammography, the gantry 15 can be adjusted at different angles to obtain images of different orientations, such as head-tail (CC) images and medial-lateral oblique (MLO) images. In one example, the gantry 15 can rotate around the axis 58 while the compression paddle 40 and the detector 18 remain stationary. In other examples, gantry 15 , compression paddle 40 , and detector 18 may rotate about axis 58 as a single unit.

[0034] In some examples, a breast imaging system such as digital mammography system 100 can be configured to perform contrast imaging, wherein a contrast agent such as iodine can be injected into a patient, which travels to a region of interest (ROI) (e.g., a lesion) within the breast. The contrast agent is absorbed into blood vessels surrounding a cancerous lesion in the ROI, thereby providing a contrast image over a period of time relative to surrounding tissue, thereby enhancing the ability to locate the lesion. In some examples, the contrast agent can additionally be absorbed by healthy breast tissue, causing the BPE to be visible in the acquired images.

[0035] The use of contrast agents can be combined with images of the ROI taken using dual energy imaging techniques and technologies. In dual energy imaging, low energy (LE) and high energy (HE) images of the ROI are taken. For each view, a pair of images is acquired: a low energy (LE) image and a high energy (HE) image. The LE and HE images are typically acquired at average energies above and below the k-edge of the contrast agent. At x-ray energies just above the k-edge of the contrast agent, the absorption of x-rays is increased, resulting in increased contrast of the iodine contrast agent in the HE image.

[0036] In dual energy 3D or stereotactic procedures, LE and HE image acquisitions are performed with the x-ray source having at least two different positions relative to the detector. The images are then recombined to show material specific information about the internal structure of the tissue being imaged. In the example of breast MRI using contrast enhancement, the contrast agent may have a different T1 that can be exploited by the pulse sequence of the MRI. In the MRI or CEM example, the contrast agent may pool in healthy breast tissue, resulting in BPE.

[0037] An example of a reconstructed CEM image 200 of a breast is shown in Figure 2 The breast in image 200 does not include a lesion or other type of suspicious area, yet there is still an area 202 that is shown as increased contrast (e.g., brighter) than the surrounding breast tissue. Area 202 may be attributable to BPE. BPE may be healthy tissue, but the level of BPE may be associated with the risk of developing a cancerous lesion. For this reason, in addition to or instead of identifying suspicious areas, clinicians may also be interested in identifying BPE in CEM or other contrast-enhanced images.

[0038] Now go to Figure 3 , a flow chart of a method 300 for displaying a BPE-free image is shown. The method 300 may use a method stored in an imaging system (e.g., Fig. 9 Imaging processing device 902 and / or Figure 1 A computing device of the digital mammography system 100) or a controller communicatively coupled to the digital mammography system (e.g., Figure 1 The method 300 may be executed by computer readable instructions in a non-transitory memory of a controller 44 of the MRI system. In alternative embodiments, the controller may be included in the MRI system or communicatively coupled to the MRI system. In some embodiments, the method 300 may be executed by another computing device (e.g., an edge device, a picture archiving and communication system (PACS)) without departing from the scope of the present disclosure.

[0039] At 301, method 300 includes acquiring a morphological image and a contrast-enhanced image from an imaging device. The morphological image may correspond to an image in which no contrast agent is captured in the image, and the contrast-enhanced image may correspond to an image in which a contrast agent is captured in the image. In some examples, the imaging device may be a digital mammography system, such as a Figure 1 The digital mammography system 100 is provided, and the morphological image may be a lower energy x-ray image, and the contrast-enhanced image may be generated by the recombination of a low energy x-ray image (e.g., a low energy image) and a high energy x-ray image. In an alternative example, the imaging device may be an MRI or a CT. Acquiring the morphological image and the contrast-enhanced image may include: before acquiring the image, administering a contrast agent intravenously, followed by image capture. A processing device such as a controller of the imaging device or a processor of the imaging system may include instructions for generating a reconstructed image from the low energy image and the high energy image. The reconstructing instructions may include performing a logarithmic weighted subtraction between the low energy image and the high energy image. The contrast-enhanced image may include an area of ​​interest in which contrast media has accumulated and is displayed as an area of ​​increased contrast compared to the background contrast of the reconstructed image. The morphological image and the contrast-enhanced image may be two-dimensional images or three-dimensional images.

[0040] At 302, method 300 includes automatically distinguishing BPE areas from suspicious areas. Automatically distinguishing BPE areas from suspicious areas may be triggered by a user requesting to view a contrast enhanced image. The user request may be received by a user input device, such as a user input device 930 of the image processing device 902 or a user input device of a workstation 43 of the digital mammography system 100. In some examples, the suspicious area may be a lesion. In alternative examples, the suspicious area may be a scar, a metal object and / or an implant. Distinguishing BPE areas from suspicious areas may include identifying a region of interest (ROI) of the image and assigning the ROI as corresponding to the BPE or to the suspicious area. Distinguishing BPE areas from suspicious areas may be automatically performed by an algorithm stored in a non-volatile memory of a controller. The algorithm may include a first algorithm configured to identify a BPE and a second algorithm configured to identify a suspicious area. In some examples, a third algorithm may be configured to identify both suspicious areas and BPE. The details of the algorithm may be relative to Fig.10 The block diagram further explains.

[0041] Go to Figure 4, shows an example of a reconstructed CEM image 400. Image 400 includes both a BPE and a lesion (e.g., a suspicious area). A first region of interest 402 and a second region of interest 404 may be segmented in image 400. The first ROI and the second ROI may be automatically segmented by an algorithm including a machine learning algorithm and / or a deep learning algorithm, or may be segmented by a clinician. In some examples, an algorithm configured to identify BPEs and suspicious areas may also include instructions for automatically segmenting regions of interest. The contrast of each of the first ROI and the second ROI may be above a threshold level above the background contrast level. The first ROI 402 may correspond to a BPE, and the second ROI 404 may correspond to a lesion. The first ROI 402 may be segmented by the following relative to Fig.10 The algorithm further described automatically distinguishes the first ROI and the second ROI 404. If the first ROI and the second ROI are not automatically distinguished as BPE and suspicious areas, a clinician viewing the image 400 may spend an increased amount of time to diagnose the patient or require a repeat or alternative imaging procedure.

[0042] Now return to Figure 3 , method 300 continues to 304 and includes automatically adjusting the appearance of the BPE. The automatic adjustment of the appearance may be performed by an adjustment algorithm stored in a memory of the controller. The automatic adjustment may occur after the automatic distinction between the BPE and the suspicious area without any additional triggering. In some examples, a user may request a desired adjustment along with a request to view the contrast enhanced image. For example, a user may request to increase, decrease, or highlight the BPE. In some examples, the adjustment algorithm may be combined with an algorithm for automatically distinguishing the BPE from the suspicious area. Fig.10 Algorithms for automatically distinguishing and adjusting BPE are further discussed.

[0043] In a first embodiment, automatically adjusting the appearance of the BPE may include reducing the contrast of the ROI corresponding to the BPE to a level below the contrast level of the ROI corresponding to the suspicious area. In some examples, automatically reducing the contrast of the BPE may include generating a plurality of BPE-reduced images, each of the plurality of BPE-reduced images may include the contrast of the BPE reduced by a stepwise amount. In some examples, the contrast level of the ROI corresponding to the BPE may be reduced to a level equivalent to the background contrast level of the image, thereby producing a BPE-free image.

[0044] In a second embodiment, automatically adjusting the appearance of the BPE may include automatically increasing contrast of the ROI corresponding to the BPE. In some examples, the contrast of the ROI corresponding to the BPE may be increased to a level higher than the contrast of the ROI corresponding to the suspicious area. In a further example, automatically increasing the contrast of the ROI corresponding to the BPE may include generating a plurality of BPE-increased images, each of the plurality of BPE-increased images may include contrast of the BPE increased by a stepwise amount.

[0045] In a third embodiment, automatically adjusting the appearance of the BPE may include highlighting the ROI corresponding to the BPE. The highlighting may include covering the ROI corresponding to the BPE with a transparent colored overlay. In some examples, the overlay may be a color different from the black, white, and grayscale colors of the contrast-enhanced image.

[0046] Now go to Figure 5 , shows an example of a reconstructed BPE-free CEM image. Image 500 may be the same as image 400, but without the BPE (e.g., without BPE). The area of ​​the first ROI 402 of image 400 may no longer be distinguishable from background breast tissue in image 500. Since the contrast level of the second ROI 404 is maintained between image 400 and image 500, the second ROI 404 may still be identified in image 500. In this way, the presence, location, and size of the suspicious area may be more easily identified by the clinician in image 500 than in image 400.

[0047] Now return to Figure 3 , method 300 continues to 306 and includes displaying an adjusted contrast-enhanced breast image. The display of the BPE may be adjusted in the adjusted contrast-enhanced breast image, and may be referred to herein as an adjusted BPE image. Displaying the adjusted BPE image may include displaying the adjusted BPE image (e.g., the adjusted contrast-enhanced image) together with the morphological image and the contrast-enhanced image without BPE reduction. In examples where images are acquired using digital mammography (e.g., contrast-enhanced mammography), the morphological image may correspond to a low-energy image, and the contrast-enhanced image may correspond to a reconstructed image. The type of arrangement of the displayed images may depend, among other things, on the clinician's preference, the complexity of the analysis, and the available screen area for displaying the images. In some examples, the type of arrangement of the displayed images may be automatically selected by the method based on the size of the display. For example, a first type of display may be automatically selected for a large format computer monitor display, and a second type of display may be automatically selected for a small format computer monitor display. The following description relative to Figures 6 to 8 An example of displaying an adjusted BPE image is discussed further. Method 300 ends.

[0048] Now go to Fig.10 , illustrates a block diagram 1000 of an example implementation of an algorithm for automatically distinguishing BPEs from suspicious regions and automatically adjusting the appearance of BPEs. Fig.10 The algorithm can be used to perform the above with respect to Figure 3 Steps 302 and 304 of the method 300 are described below. Fig.10 The described algorithm may be stored as instructions in a non-transitory memory of a controller. The algorithm may be stored in a non-transitory memory of the same controller storing the instructions of the method 300 or a different controller.

[0049] The training input 1002 may be a training image pair for the identification algorithm. The first portion 1004 of the training pair may be an image of a breast in which contrast is not highlighted (e.g., a low energy image of a CEM procedure) and a corresponding contrast-enhanced image (e.g., a reconstructed image of a CEM procedure). The second portion 1006 of the training pair may be a ground truth, in which the corresponding contrast-enhanced image has been segmented. In some examples, the ground truth may be an image segmented by a clinician. In an alternative example, the ground truth may be provided by a segmentation algorithm and reviewed by a clinician. As an embodiment, the ground truth may include a BPE segmentation image 1008. The BPE segmentation image 1008 may include a contrast-enhanced image in which a ROI corresponding to a BPE has been segmented and identified as a BPE. As an alternative embodiment, the ground truth may include a suspicious region segmentation image 1010. The suspicious region segmentation image may include a contrast-enhanced image in which a ROI corresponding to a suspicious region (such as a lesion) has been segmented and identified. In some examples, the ground truth may include both the BPE segmentation image 1008 and the suspicious region segmentation image 1010. In examples where the ground truth includes both the BPE segmentation image 1008 and the suspicious region segmentation image 1010, they may be included in the same image and / or different images.

[0050] The training input 1002 may be used to train one or more algorithms. The one or more algorithms may include an identification algorithm 1014 and an adjustment algorithm 1016. The identification algorithm 1014 may be used to perform step 302 of the method 300, and the adjustment algorithm 1016 may be used to perform step 304 of the method 300. In some examples, the identification algorithm 1014 and the adjustment algorithm 1016 may be combined into a single hybrid algorithm 1012 that is trained using both the BPE segmentation image 1008 and the suspicious region segmentation image 1010. As an example, the single hybrid algorithm 1012 may be a machine learning / deep learning algorithm that is configured to transform an image to highlight or erase BPE from a contrast-enhanced breast image. The acquired image 1042 may be input into the single hybrid algorithm 1012, and the single hybrid algorithm 1012 may output an adjusted BPE image 1044. Combining the identification algorithm 1014 and the adjustment algorithm 1016 into a single hybrid algorithm 1012 may improve the computational efficiency of steps 302 and 304.

[0051] The identification algorithm may include a BPE algorithm 1018 trained to identify BPEs. Examples of the second portion 1006 of the training pair where the ground truth includes the BPE segmentation image 1008 may be used to train the BPE algorithm 1018, as indicated by dashed arrow 1017. The BPE algorithm 1018 may automatically identify a ROI of the contrast-enhanced breast image as corresponding to a BPE. Additionally, examples of the second portion 1006 of the training pair where the ground truth includes the suspicious region segmentation image 1010 may be used to train a suspicious region algorithm 1020, as indicated by dashed arrow 1019. The suspicious region algorithm 1020 may automatically identify a ROI of the contrast-enhanced breast image as corresponding to a suspicious region.

[0052] Once trained, the acquired image 1042 may be input into the identification algorithm 1014. The acquired image 1042 may be an acquired contrast-enhanced breast image, such as the contrast-enhanced breast image acquired at step 301 of the method 300. The trained BPE algorithm 1018 and the trained suspicious region algorithm 1020 together may automatically distinguish BPE from suspicious regions of the acquired image 1042.

[0053] As an example, the BPE algorithm 1018 and the suspicious region algorithm 1020 may each use contrast levels to identify regions corresponding to BPE and regions corresponding to suspicious regions. The contrast enhancement attributed to BPE may be less than the contrast enhancement attributed to the suspicious region. In this way, a contrast threshold may be used to distinguish a ROI as corresponding to BPE or corresponding to a suspicious region. As an alternative example, the BPE algorithm 1018 and the suspicious region algorithm 1020 may each be a machine learning algorithm, such as a deep learning algorithm. The machine learning algorithm may be an algorithm that performs a segmentation task. As an example, the machine learning algorithm may be Unet, Vnet, or Mask-RCNN, etc. In yet another example, when contrast-enhanced breast images are acquired using CEM, the BPE algorithm 1018 and the suspicious region algorithm 1020 may each be based on acquisition time. During a CEM examination, multiple CEM low-energy and high-energy x-ray image pairs (e.g., CC and MLO views) may be acquired over time. Contrast media may be gathered in lesions or suspicious regions before converging in healthy breast tissue to cause BPE. To this end, the algorithm may identify a ROI with contrast enhancement in a CEM image collected before a threshold time as the ROI corresponding to a lesion or suspicious region. Any additional ROIs with increased contrast appearing in a reconstructed x-ray image acquired after the threshold time may then be identified at the ROI corresponding to the BPE. More generally, the BPE or suspicious lesion algorithm may be applied to multiple CEM images of various views acquired during an examination, and timing information may be used as input.

[0054] Alternatively, the suspicious region algorithm 1020 may be a machine learning algorithm, such as a deep learning algorithm. For example, the algorithm may include a You Only Look Once (YOLO) architecture. Additionally or alternatively, the suspicious region algorithm 1020 may utilize radiomics feature extraction and classification, as well as other imaging processing tools to identify suspicious regions in contrast-enhanced breast images.

[0055] As an alternative embodiment of the identification algorithm 1014, the identification algorithm 1014 may include a combined BPE and suspicious area algorithm 1022. As indicated by arrow 1023, both the BPE segmentation image 1008 and the suspicious area segmentation image 1010 may be used in combination as ground truth to train the combined BPE and suspicious area algorithm 1022. When the acquired image 1042 is input, the combined BPE and suspicious area algorithm 1022 can distinguish between BPE and suspicious areas. As an example, the BPE and suspicious area algorithm 1022 can be a machine learning / deep learning algorithm that performs multi-instance segmentation, such as but not limited to Mask-RCNN. Combining BPE and suspicious area identification into a single multi-task algorithm can reduce the amount of manual time required to train the algorithm and can further improve the computational efficiency of the identification algorithm 1014.

[0056] In some embodiments, the output of the trained suspicious region algorithm 1020 can be combined with the BPE segmentation image 1008 for training the BPE algorithm 1018, as indicated by the combination of arrow 1017 and arrow 1021. In other words, the suspicious region algorithm 1020 can be first trained using the ground truth including the suspicious region segmentation 1010. The contrast-enhanced image can then be input to the suspicious region algorithm 1020, which outputs a contrast image in which the ROI corresponding to the suspicious region is segmented. In addition to the BPE segmentation image 1008, the output identifying the ROI corresponding to the suspicious region can also be used to train the BPE algorithm 1018. In this way, the suspicious region algorithm 1020 has detected suspicious regions (such as lesions or foreign bodies) and other artifacts (such as nipples) that do not affect BPE, and the accuracy of the BPE algorithm 1018 can be improved. In one embodiment, image regions that are above a certain threshold but are not suspicious regions can be considered BPE.

[0057] The adjustment algorithm 1016 may be configured to receive the output of the identification algorithm 1014 and automatically adjust the display of the BPE. The adjustment algorithm 1016 may be an image processing algorithm with instructions for blending or fusing the colors of pixels according to the desired output. In an alternative example, the adjustment algorithm may be a deep learning network configured to highlight areas and / or features of an image.

[0058] The adjustment algorithm 1016 may include a contrast reduction algorithm 1028. The contrast reduction algorithm 1028 may be configured to reduce the contrast of the ROI identified as corresponding to the BPE. As an example, the contrast may be reduced to equal the background contrast level. In an alternative embodiment, the adjustment algorithm 1016 may include an increase contrast algorithm 1030. The increase contrast algorithm 1030 may be configured to increase the contrast of the ROI identified as corresponding to the BPE. As an example, the contrast may be increased to be equal to or greater than the contrast of the ROI identified as corresponding to the suspicious area. In an alternative embodiment, the adjustment algorithm 1016 may include a highlight area algorithm 1032. The highlight area algorithm 1032 may be configured to overlay a partially transparent color image corresponding to the ROI identified as the BPE on the contrast-enhanced image. The partially transparent color image may help the clinician distinguish the BPE from the rest of the image.

[0059] In one embodiment, the output of the BPE algorithm 1018 may be an input to the adjustment algorithm 1016, as indicated by arrow 1024. The output of the BPE algorithm 1018 fed into the adjustment algorithm 1016 may be based on training the BPE segmented image 1008 (arrow 1017), or may be based on training using the suspicious regions algorithm 1020 (arrow 1021), followed by training using the BPE segmented image 1008 (arrow 1017). In an alternative embodiment, the output of the BPE algorithm 1018 may be combined with the output of the suspicious regions algorithm 1020 (along arrow 1025) as an input to the adjustment algorithm 1016. The BPE algorithm 1018 may be combined with the suspicious regions algorithm 1020 sequentially (e.g., the suspicious regions algorithm 1020 followed by the BPE algorithm 1018) or simultaneously.

[0060] In another embodiment, the output of the BPE and suspicious region algorithm 1022 may be an input (along arrow 1026) to the adjustment algorithm 1016. The adjusted BPE image 1044 may be output after sequential iterations of the identification algorithm 1014 and the adjustment algorithm 1016 and / or as the output of a single hybrid algorithm 1012.

[0061] An example of a possible display of the adjusted BPE image 1044 is shown in Figures 6 to 8 The displayed images may include a morphology image (e.g., a breast image without contrast enhancement), a contrast-enhanced breast image (e.g., a contrast-enhanced image), and a corresponding contrast-enhanced breast image with an adjusted BPE (e.g., a contrast-enhanced adjusted BPE image). In some examples, the images may be acquired by a CEM examination, and the morphology image may include a low-energy image, and the contrast-enhanced image may be a reconstructed contrast-enhanced image, and the contrast-enhanced image with an adjusted BPE may be an adjusted reconstructed image.

[0062] Figure 6 A first example 600 of a display 602 is shown showing a morphology image 604, contrast enhanced using BPE 606, and a contrast enhanced adjusted BPE image 608. The contrast enhanced image 606 using BPE may be an unadjusted contrast enhanced breast image. The contrast enhanced adjusted BPE image 608 may be an adjusted algorithm (such as Fig.10The output of the adjustment algorithm 1016). In some examples, the contrast-enhanced adjusted BPE image 608 can be a BPE-free image. In an alternative example, the contrast-enhanced adjusted BPE image 608 can enhance the contrast of the BPE or highlight the BPE area. As an example, the display 602 can be a large display, such as the entire area of ​​a computer monitor. Example 600 can show a morphological image 604 on the leftmost portion of the display 602. A contrast-enhanced image 606 using BPE can be placed to the right of the morphological image 604. The contrast-enhanced adjusted BPE image 608 can be positioned to the right of the contrast-enhanced image 606 using BPE. Other arrangements of the morphological image 604, the contrast-enhanced image 606 using BPE, and the contrast-enhanced adjusted BPE image 608, each of which is fully visible on the display 602 at the same time, have also been considered. In some examples, the first example 600 can be a first type of display that is automatically selected for a large format display.

[0063] Figure 7 A second example 700 of a display 702 is shown, which in a first example 710 may show a morphological image 704. In a second example 712, the display 702 may show a contrast image 706 enhanced using BPE. In the transition from the first example 710 to the second example 712, a gradient effect may be used, wherein the transparency of the morphological image 704 gradually increases while reducing the transparency of the contrast image 706 enhanced using BPE in the same screen area. In a third example 714, the display 702 may show a contrast-enhanced adjusted BPE image 708. In some examples, the contrast-enhanced adjusted BPE image 708 may be a BPE-free image. In an alternative example, the contrast-enhanced adjusted BPE image 708 may include an enhanced or highlighted BPE. Similarly, a gradient effect may be used to transition between the second example 712 and the third example 714. In this manner, a morphological image 704, a contrast image 706 enhanced with BPE, and a contrast-enhanced adjusted BPE image 708 may be sequentially shown. In some examples, the order of the first instance 710, the second instance 712, and the third instance 714 may be reversed or swapped. Sequential viewing may be desirable when a display such as display 702 has a reduced area (such as a minimized window) and / or a mobile device and multiple image views as shown in the first example 600 would make the image too small, thereby obscuring the details needed by the clinician to perform analysis. Additionally, a gradient effect may be overlaid on the image, which may allow for easier comparison and analysis by the clinician.

[0064] In some examples, the displayed image (e.g., morphology image 704, contrast image enhanced with BPE 706, and / or contrast enhanced adjusted BPE image 708) may be of height 718 and width 720, and the display 702 may be of height 722 and width 724. The ratio of height to width may be referred to as a form factor. The form factor of the displayed image may depend on the imaging device (e.g., Figure 1 The adjustment algorithm 1016 may be a setting of the digital mammography system 100 and may be a fixed value. In other words, the adjustment algorithm 1016 may not adjust the shape factor of the BPE image. Adjusting the shape factor of the displayed image may result in undesirable distortion of the displayed image. To this end, the shape factor of the displayed image may remain constant and may not be adjusted to match the shape factor of the display. For example, if the display is rotated, the shape factor of the display may change, and the shape factor of the displayed image may not change. Figure 7 Displaying images sequentially as shown in may be desirable to maintain the form factor of the displayed image while also maintaining a displayed image large enough for a clinician to make an accurate diagnosis.

[0065] Figure 8A third example 800 of a display 802 is shown, which in a first example 812 may show a morphological image 804. In a second example 814, the display 802 may show a contrast image 806 enhanced using BPE. In a third example 816, the display 802 may show a contrast-enhanced image 808 using a first level of BPE. In a fourth example 818, the display 802 may show a contrast-enhanced image 810 using a second level of BPE. In some examples, the contrast difference between the BPE region and the background in the BPE image 808 of the first contrast enhancement level may be different from the contrast difference between the BPE region and the background in the BPE image 810 of the second contrast enhancement level. In other words, the contrast of the BPE in the image 808 may be different from the contrast of the BPE in the image 810. In some examples, the contrast 808 of the first level of BPE may be greater than the BPE 810 of the second level. In an alternative example, the contrast of the BPE in the image 808 may be less than the BPE 810 of the second level. In an alternative example, a first level of contrast enhanced BPE 808 may be highlighted in an overlay of a first transparency, and a second level of BPE may include the same overlay having a second transparency, the first transparency being greater than the second transparency. In some examples, the image 810 having a second reduced level of BPE may be a BPE-free image. In some examples, the third example 800 may include additional instances of levels of BPE between the first reduced level and the second reduced level. The clinician may transition from displaying the first instance 812 and subsequent instances (e.g., the second instance 814, the third instance 816, etc.) by scrolling. Scrolling may include transitions between instances, wherein the first instance moves away from the display 802 in a first direction while the next instance simultaneously moves onto the screen from a second direction. In this manner, the clinician may view the morphological image 804, recombined in a sequential manner with the BPE image 806 and a plurality of adjusted BPE images (including, for example, the first BPE level image 808 and the second BPE level image 810). In some examples, transitions between instances (e.g., the first instance 812 and the second instance 814) may be as described above with respect to Figure 7 The described fade transition, or instance may be immediately replaced by a subsequent instance without a fade transition or scroll transition.

[0066] The technical effect of method 300 is to automatically generate a contrast-enhanced breast image in which the presentation of the BPE is adjusted to be different from the presentation of suspicious areas (such as lesions). In some examples, the BPE can be removed from the contrast-enhanced image, or in an alternative example, the BPE can be highlighted. The BPE corresponds to healthy tissue, and automatically reducing or removing the BPE can allow clinicians to accurately and precisely determine the presence and location of possible cancerous lesions. In addition, the method of displaying the relevant image to the clinician can be adjusted to adapt to a minimized window or mobile device display. In this way, the efficiency and accuracy of screening contrast-enhanced breast images can be improved.

[0067] The present disclosure also provides support for a method, the method comprising: automatically distinguishing a first region of interest (ROI) of a contrast-enhanced breast image from a second ROI of the contrast-enhanced breast image, wherein the first ROI corresponds to background parenchymal enhancement (BPE) and the second ROI corresponds to a suspicious region; automatically adjusting the appearance of the first ROI and generating an adjusted BPE image; and displaying the contrast-enhanced breast image and the adjusted BPE image at a display. In a first example of the method, automatically distinguishing the first ROI from the second ROI comprises inputting the contrast-enhanced breast image to a BPE algorithm trained using an image pair and a BPE segmentation image. In a second example of the method, optionally including the first example, the method further comprises: training a suspicious region algorithm using the image pair and the suspicious region segmentation image, and after training the suspicious region algorithm, training a BPE algorithm using the output of the suspicious region algorithm, the trained BPE algorithm being used to automatically distinguish the first ROI from the second ROI. In a third example of the method, optionally including one or both of the first and second examples, automatically distinguishing the first ROI from the second ROI and automatically adjusting the appearance comprises inputting the contrast-enhanced breast image to a single hybrid algorithm. In a fourth example of the method, optionally including one or more or each of the first to third examples, displaying the contrast-enhanced breast image and the adjusted BPE image includes displaying the contrast-enhanced breast image and the adjusted BPE image simultaneously. In a fifth example of the method, optionally including one or more or each of the first to fourth examples, displaying the contrast-enhanced breast image and the adjusted BPE image includes sequentially displaying the contrast-enhanced breast image and the adjusted BPE image. In a sixth example of the method, optionally including one or more or each of the first to fifth examples, the display is a mobile device. In a seventh example of the method, optionally including one or more or each of the first to sixth examples, the method further includes: after displaying the contrast-enhanced breast image and the adjusted BPE image, gradually or scrolling between an instance showing the contrast-enhanced breast image and an instance showing the adjusted BPE image. In an eighth example of the method, optionally including one or more or each of the first to seventh examples, the contrast-enhanced breast image is a reconstructed image acquired by a contrast-enhanced mammography examination.

[0068] The present disclosure also provides support for an image processing system, the system comprising: a display device; an image processing device, the image processing device being communicatively coupled to the display device and comprising a processor and a non-transitory memory storing instructions, the instructions being executable by the processor to: use a BPE algorithm that has been trained using an image pair including a ground truth background parenchymal enhancement (BPE) segmentation image and a suspicious region algorithm that has been trained using an image pair including a ground truth suspicious region segmentation image, distinguish a region of interest (ROI) of a contrast-enhanced breast image corresponding to the BPE, use an adjustment algorithm to adjust the ROI of the contrast-enhanced breast image corresponding to the BPE, and output the adjusted contrast-enhanced breast image to the display device. In a first example of the system, the instructions for adjusting the ROI of the contrast-enhanced breast image corresponding to the BPE also include instructions for: increasing the contrast of the ROI of the contrast-enhanced breast image corresponding to the BPE, decreasing the contrast of the ROI of the contrast-enhanced breast image corresponding to the BPE, or highlighting the ROI of the contrast-enhanced breast image corresponding to the BPE. In a second example of the system, optionally including the first example, the instructions further include outputting an unadjusted contrast-enhanced breast image and a corresponding contrast-enhanced breast image without enhanced contrast. In a third example of the system, optionally including one or both of the first and second examples, the instructions for adjusting the ROI of the contrast-enhanced breast image include adjusting the ROI of the contrast-enhanced breast image to a first level and adjusting the ROI of the contrast-enhanced breast image to a second level. In a fourth example of the system, optionally including one or more or each of the first to third examples, the instructions include sequentially outputting a contrast-enhanced breast image adjusted to a first level and a contrast-enhanced breast image adjusted to a second level. In a fifth example of the system, optionally including one or more or each of the first to fourth examples, the BPE algorithm and the suspicious region algorithm are machine learning algorithms. In a sixth example of the system, optionally including one or more or each of the first to fifth examples, the BPE algorithm and the suspicious region algorithm are included in a combined BPE and suspicious region algorithm. In a seventh example of the system, optionally including one or more or each of the first to sixth examples, an output of the BPE algorithm and an output of the suspicious region algorithm are sequential or simultaneous inputs to the conditioning algorithm.

[0069] The present disclosure also provides support for a system for digital mammography, the system comprising: an x-ray source in communication with a detector; a display device; and a computing device in communication with the display device and the detector, the computing device comprising a processor and a non-volatile memory storing instructions, the instructions executable by the processor to: acquire a low-energy x-ray image and a high-energy x-ray image, output a reconstructed image based on the low-energy x-ray image and the high-energy x-ray image, and identify background parenchymal enhancement (BPE) in the reconstructed image and adjust the reconstructed image, and output the adjusted reconstructed image to the display device. In a first example of the system, the instructions for identifying the BPE and adjusting the reconstructed image are included in a single hybrid algorithm. In a second example of the system, optionally including the first example, the instructions for identifying the BPE in the reconstructed image are based on a contrast threshold.

[0070] As used herein, the elements or steps listed in the singular and beginning with the word "one" or "an" should be understood as not excluding a plurality of the elements or steps, unless such exclusion is explicitly stated. In addition, the reference to "one embodiment" of the present invention is not intended to be interpreted as excluding the existence of additional embodiments that also include the cited features. In addition, unless explicitly stated to the contrary, "comprising", "including" or "having" an embodiment of an element or multiple elements with a specific characteristic may include additional such elements that do not have the characteristic. The terms "including" and "in..." are used as the concise language equivalents of the corresponding terms "including" and "wherein". In addition, the terms "first", "second" and "third" etc. are only used as marks, and are not intended to impose numerical requirements or specific positional order on their objects.

[0071] This written description uses examples to disclose the invention, including the best mode, and also to enable a person skilled in the relevant art to practice the invention, including making and using any devices or systems and performing any included methods. The patentable scope of the invention is defined by the claims, and may include other examples that occur to a person 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 insignificant differences from the literal language of the claims.

Claims

1. A method, comprising: automatically distinguishing a first region of interest (ROI) of a contrast-enhanced breast image, wherein the first ROI corresponds to background parenchymal enhancement (BPE); automatically adjusting the appearance of the first ROI and generating an adjusted BPE image; as well as The contrast enhanced breast image and the adjusted BPE image are displayed at a display.

2. The method of claim 1 , further comprising automatically distinguishing a second ROI of the contrast-enhanced breast image, wherein the second ROI corresponds to a suspicious region, and automatically distinguishing the first ROI from the second ROI, comprising inputting the contrast-enhanced breast image to a BPE algorithm trained using the contrast-enhanced breast image and the BPE segmentation image.

3. The method according to claim 2, wherein the method further comprises training a suspicious region algorithm using the contrast-enhanced breast image and the suspicious region segmentation image, and after training the suspicious region algorithm, training a BPE algorithm using the output of the suspicious region algorithm, wherein the trained BPE algorithm is used to automatically distinguish the first ROI from the second ROI.

4. The method of claim 2, wherein automatically differentiating the first ROI from the second ROI and automatically adjusting the appearance comprises inputting the contrast-enhanced breast image to a single hybrid algorithm.

5. The method of claim 1, wherein displaying the contrast-enhanced breast image and the adjusted BPE image comprises displaying the contrast-enhanced breast image and the adjusted BPE image simultaneously.

6. The method of claim 1, wherein displaying the contrast-enhanced breast image and the adjusted BPE image comprises sequentially displaying the contrast-enhanced breast image and the adjusted BPE image. The method of claim 6 , wherein the display is a mobile device.

8. The method according to claim 6, wherein the method further comprises: After displaying the contrast enhanced breast image and the adjusted BPE image, fade or scroll between an instance showing the contrast enhanced breast image and an instance showing the adjusted BPE image.

9. The method of claim 1, wherein the contrast-enhanced breast image is a reconstructed image acquired by a contrast-enhanced mammography examination.

10. An image processing system, comprising: Display devices; An image processing device communicatively coupled to the display device and comprising a processor and a non-transitory memory storing instructions executable by the processor to: using a BPE algorithm that has been trained using an image pair including a ground truth background parenchyma enhancement (BPE) segmentation image and a suspicious region algorithm that has been trained using an image pair including a ground truth suspicious region segmentation image, distinguishing a region of interest (ROI) of the contrast-enhanced breast image corresponding to the BPE; adjusting the ROI of the contrast-enhanced breast image corresponding to the BPE using an adjustment algorithm; and The adjusted contrast enhanced breast image is output to the display device.

11. The image processing system of claim 10, wherein the instructions for adjusting the ROI of the contrast-enhanced breast image corresponding to BPE further comprise instructions for: increasing contrast of the ROI of the contrast-enhanced breast image corresponding to BPE, decreasing contrast of the ROI of the contrast-enhanced breast image corresponding to BPE, or highlighting the ROI of the contrast-enhanced breast image corresponding to BPE.

12. The image processing system of claim 10, wherein the instructions further comprise outputting an unadjusted contrast-enhanced breast image and a corresponding contrast-enhanced breast image without enhanced contrast.

13. The image processing system of claim 10, wherein the instructions to adjust the ROI of the contrast-enhanced breast image corresponding to BPE include instructions to adjust the ROI of the contrast-enhanced breast image to a first level and to adjust the ROI of the contrast-enhanced breast image to a second level.

14. The image processing system of claim 13, wherein the instructions include instructions to sequentially output the contrast-enhanced breast image adjusted to the first level and the contrast-enhanced breast image adjusted to the second level.

15. The image processing system according to claim 10, wherein the BPE algorithm and the suspicious region algorithm are machine learning algorithms.

16. The image processing system of claim 10, wherein the BPE algorithm and the suspicious region algorithm are included in a combined BPE and suspicious region algorithm.

17. The image processing system of claim 10, wherein the output of the BPE algorithm and the output of the suspicious region algorithm are sequential or simultaneous inputs to the conditioning algorithm.

18. A system for digital mammography, the system comprising: an x-ray source in communication with the detector; Display devices; and a computing device in communication with the display device and the detector, the computing device comprising a processor and a non-transitory memory storing instructions executable by the processor to: Acquire low energy x-ray images and high energy x-ray images; outputting a reconstructed image based on the low-energy x-ray image and the high-energy x-ray image; and identifying background parenchymal enhancement (BPE) in the reconstructed image and adjusting the reconstructed image; and The adjusted reconstructed image is output to the display device.

19. The system of claim 18, wherein the instructions to identify BPEs and adjust the recombined image are included in a single hybrid algorithm.

20. The system of claim 18, wherein the instructions to identify a BPE in the reconstructed image are based on a contrast threshold.

Images