Systems and methods for generating predictive views for improved mammography imaging system localization

Abstract

The disclosure relates to systems and methods for generating predictive views for improved mammography imaging system localization. An X-ray imaging system adapted to perform a diagnostic imaging procedure comprises: a radiation source; a detector adapted to receive radiation emitted from the radiation source to generate image data; a controller operably connected to the radiation source and the detector to control operation of the radiation source and the detector to generate image data, the controller comprising a central processing unit and an interconnected electronic storage unit for processing the image data from the detector; a display operably connected to the controller; and a user interface operably connected to the controller to enable user input to the controller. The X-ray imaging system also includes an image prediction module operably connected to the controller and configured to receive a previous screening image of the patient and generate a predicted view of the patient for presentation on the display.

Description

Technical Field

[0001] The present disclosure generally relates to medical imaging systems, and more particularly to mammographic imaging and biopsy systems. Background Art

[0002] Embodiments of the present invention generally relate to X-ray medical imaging, and more particularly to devices, systems, and methods for performing various imaging procedures, such as mammographic imaging procedures, including but not limited to spectral mammography (SM), such as 2D / 3D dual-energy contrast-enhanced (CE) mammography, full-field digital mammography (FFDM), or digital breast tomosynthesis (DBT) mammography.

[0003] Spectral mammography (SM) is an X-ray imaging modality used to scan the breast for screening, diagnosis, and / or interventional procedures. The effectiveness of mammography is affected by numerous factors, one of which is the two-dimensional (2D) rendering of the images obtained using SM.

[0004] Alternative systems for SM are also known for breast imaging. Some examples include full-field digital mammography that captures images directly onto a flat-panel detector, computed radiography involving the use of cassettes containing imaging plates, or digital breast tomosynthesis (DBT). Digital breast tomosynthesis (DBT) or mammo-tomo systems are dedicated mammography systems that acquire a number (e.g., dozens) of angularly offset projection X-ray images and reconstruct a three-dimensional (3D) image dataset using the resulting X-ray image data.

[0005] The 3D image dataset is used to form various volumetric representations of the imaged breast, including the entire 3D volume of the breast, as well as various 3D segments of the 3D volume, such as slices or slabs of a specified thickness that make up the 3D volume and are oriented to provide a desired view of one or more regions of interest (ROIs) detected within the 3D image dataset.

[0006] In addition, when 3D image datasets of the breast have been generated, after being used in appropriate diagnostic procedures, these 3D image datasets can be used to guide a biopsy device used with a DBT system into the breast to obtain a biopsy of a region of interest (ROI) identified within the 3D image dataset. In a DBT system, the biopsy device is directly mounted on the DBT system so that a biopsy can be performed using the biopsy device and stereo camera images of the breast or by using the 3D image dataset, and subsequently the biopsy device is triangulated to the ROI in the breast to guide the biopsy device to the ROI.

[0007] Regarding the use of these mammography imaging systems, in an initial screening imaging procedure, a patient's breast will be imaged in a plurality of standardized views, the plurality of standardized views including but not limited to a craniocaudal (CC) view and a mediolateral oblique (MLO) view. Images of these two views obtained by the mammography imaging system can be examined to determine the presence of any lesions, calcifications, or other ROIs within the breast. If any such ROI is located, the patient may be recalled for a subsequent diagnostic imaging procedure to obtain additional breast images, such as spot compression (SPOT) or magnification (MAG) views obtained in a corresponding imaging procedure, or even to perform a biopsy on the ROI identified within the breast in the screening images (i.e., the CC image and the MLO image).

[0008] Since, in many cases, a significant amount of time elapses between the screening imaging procedure and the diagnostic imaging procedure (e.g., a MAG imaging procedure and / or a biopsy procedure), the patient must be repositioned on the mammography imaging system in order to perform the MAG procedure and / or the biopsy procedure. In each of these types of procedures, when repositioned on the mammography imaging system, an image of the ROI within the breast is obtained. However, in each diagnostic procedure, the area imaged by the mammography imaging system is focused on the ROI such that the area of the breast imaged by the radiation source of the mammography imaging system is much smaller than in the screening imaging procedure.

[0009] As a result of imaging a much smaller area within the breast that contains only the ROI in the diagnostic imaging procedure, it is necessary to accurately position the breast on the mammography imaging system such that the ROI is aligned within the field of view (FoV) of the radiation source. More specifically, diagnostic imaging procedures (e.g., a MAG procedure and / or a biopsy procedure) typically require acquisition of a lateral medial (LM) and / or a mediolateral (ML) view of the breast prior to performing the procedure in order to reliably assess the position of the ROI within the breast, including estimating the distance relative to anatomic landmarks such as the nipple, and thus to allow proper positioning of the ROI within the FOV for the diagnostic imaging procedure.

[0010] However, the ML / LM views may not be available when performing the diagnostic imaging procedure. In such a case, the only information available to the technician regarding the position of the ROI is the ROI localization in the CC view and / or the MLO view. In order to place the ROI within the FoV, the technician must mentally / manually estimate or guess the position of the ROI in the LM / ML view, particularly with respect to landmarks on the breast (e.g., the nipple).

[0011] The technique used for mental / manual estimation of the localization is referred to as breast lesion triangulation, and in Mammopathy Triangulation: Review and Clinical Applications(Jeong Mi Park, MD and Edmund A. Franken Jr) and discusses common misuses of the technique. Since the process of performing triangulation of breast lesions makes certain assumptions about the breast's anatomy and is often incorrectly applied, multiple diagnostic images (SPOT, MAG, biopsy) must often be obtained to correctly localize the ROI for the diagnostic procedure, which greatly reduces the patient's effectiveness and comfort while significantly increasing the time required to perform the diagnostic procedure.

[0012] Accordingly, with respect to the setting and execution of diagnostic imaging procedures on a mammography imaging system, particularly with respect to SPOT, MAG, and biopsy imaging and / or diagnostic procedures, it is desirable to develop a system and method for accurately determining the localization of an ROI within the breast using only information already available in the CC view and the MLO view obtained from a previous screening imaging procedure performed on the breast, so as to correctly align the ROI within the FoV. Summary of the Invention

[0013] According to one aspect of an exemplary embodiment of the present disclosure, an X-ray imaging system adapted to provide patient positioning assistance during the performance of a diagnostic imaging procedure includes: a radiation source; a detector adapted to receive radiation emitted from the radiation source to generate image data; a controller operably connected to the radiation source and the detector to control the operation of the radiation source and the detector to generate the image data, the controller including a central processing unit and an interconnected electronic storage unit for processing the image data from the detector; a display operably connected to the controller for presenting an image formed by the image data; a user interface operably connected to the controller to enable user input to the controller; and an image prediction module operably connected to the controller and configured to receive a previous screening image of a patient and generate a predicted view of the patient for presentation on the display. The predicted view is a simulated image / diagram of the breast in a predefined view (ML, LM, or other view).

[0014] According to yet another aspect of an exemplary embodiment of the present disclosure, a biopsy locator adapted to be fastened to a medical imaging system to perform a biopsy procedure thereon includes a base adapted to engage a support structure on the medical imaging system and a positioning arm connected to the base, the positioning arm including a first arm movably connected to the base and a second arm movably connected to the first arm, wherein the first arm is capable of moving between lateral positions on opposite sides of the base.

[0015] According to another aspect of the exemplary embodiments of the present disclosure, a method for providing patient positioning assistance to perform a diagnostic imaging procedure on an X-ray imaging system includes the steps of: providing an X-ray imaging system having: a radiation source; a detector; a controller operably connected to the radiation source and the detector to control the operation of the radiation source and the detector to generate image data, the controller including a central processing unit and an interconnected electronic storage unit for processing the image data from the detector; a display operably connected to the controller for presenting an image formed from the image data; a user interface operably connected to the controller to enable user input to the controller; and an image prediction module operably connected to the controller and configured to generate a predicted view of the patient from one or more previous screening images of the patient for presentation on the display; supplying the one or more previous screening images to the image prediction module; generating the predicted view of the patient; and presenting the predicted view of the patient on the display.

[0016] These and other exemplary aspects, features, and advantages of the present invention will become apparent from the following detailed description taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings illustrate the presently contemplated best mode of practicing the invention.

[0018] In the drawings:

[0019] Figure 1 is a perspective view of an X-ray imaging device in the form of a mammography imaging system for imaging breast tissue of a patient according to an embodiment of the present disclosure.

[0020] Figure 2 is Figure 1 a diagram of the system showing the radiation source of the mammography imaging system in a scanning position according to an embodiment of the present disclosure.

[0021] Figure 3 is according to an embodiment of the present disclosure Figure 1 an isometric view of a mammography imaging system including a biopsy device fastened to the mammography system.

[0022] Figure 4 is according to an embodiment of the present disclosure Figure 3 an isometric view of a mammography imaging system including a magnification bracket fastened to the mammography imaging system.

[0023] Figure 5of a mammography imaging system including an image prediction module according to an embodiment of the present disclosure Figure 1 Schematic diagram of

[0024] Figure 6 is according to an embodiment of the present disclosure Figure 5 Schematic diagram of a first embodiment of an operation method of an image prediction module

[0025] Figure 7 is according to an embodiment of the present disclosure Figure 1 Schematic diagram of a display of a mammography imaging device

[0026] Figure 8 is according to an embodiment of the present disclosure Figure 6 Schematic diagram of a first embodiment of a method

[0027] Figure 9 is according to an embodiment of the present disclosure Figure 6 Schematic diagram of a second embodiment of a method

[0028] Figure 10 is according to an embodiment of the present disclosure Figure 5 Schematic diagram of a second embodiment of an operation method of an image prediction module Detailed implementation manners

[0029] One or more specific embodiments will be described below. To provide a concise description of these embodiments, not all features of actual specific implementations may be described in the specification. It should be understood that, as in any engineering or design project, in the development of any such actual specific implementation, numerous specific implementation-specific decisions must be made to achieve the developer's specific goals, such as complying with system-related and business-related constraints that may vary among specific implementations. In addition, it should be understood that such development efforts may be complex and time-consuming, but still a routine task in design, fabrication, and manufacturing for those of ordinary skill in the art who benefit from the present disclosure.

[0030] When introducing the elements of various embodiments of the present invention, the articles "a", "an", "the", and "said" are intended to mean that there is one or more such elements. The terms "comprising", "including", and "having" are intended to be inclusive and mean that there may be additional elements in addition to the listed elements. Moreover, any numerical examples in the following discussion are intended to be non-limiting, and thus additional numerical values, ranges, and percentages are within the scope of the disclosed embodiments.

[0031] As used herein, "electrically coupled", "electrically connected", and "electrically communicating" mean that the recited elements are directly or indirectly connected such that current can flow from one to the other. The connection can include direct conductive connection (i.e., without intervening capacitance, inductance, or active elements), inductive connection, capacitive connection, and / or any other suitable electrical connection. There may be intervening components.

[0032] In addition, although the embodiments disclosed herein are described with respect to a mammography device for two-dimensional imaging of breast tissue, it should be understood that the embodiments of the present invention are applicable to other types of imaging devices for both two-dimensional and three-dimensional imaging (including, for example, fluoroscopy, full-field digital mammography, digital breast tomosynthesis (DBT), and spectral mammography (mono- or multi-energy)), as well as other types of imaging devices for imaging procedures of tissues other than breast tissue. Additionally, the embodiments of the present invention are generally applicable to the analysis of tissues and are not limited to the analysis of human tissues.

[0033] Now referring to Figure 1 and Figure 2 , there is shown the main components of an exemplary radiographic imaging system 10 configured as a mammography device or system 12 for imaging breast tissue in accordance with an embodiment of the present invention. The mammography system 12 includes a radiation source / X-ray source 16, a radiation detector 18, and a collimator 20, such as the systems disclosed in U.S. Patent Application Publication No. US20200060632 entitled Apparatus And Method For Mammographic Breast Compression and U.S. Patent Application Serial No. 18 / 110,062 entitled Mammography Imaging System with Universal Attachment Structures, the entire contents of which are hereby expressly incorporated by reference herein for all purposes. The radiation source 16 is movable relative to the detector 18 between a plurality of imaging positions and is operable to emit radiation rays 22 ( Figure 2 ), which are received by the radiation detector 18 to provide an image of an object such as a breast 52. In an embodiment, the mammography system 12 may include a patient shield 24 mounted to the radiation source 16 via a shield rail 26 to prevent the patient's head from obstructing the radiation rays and to protect the patient from the radiation rays 22.

[0034] Still further referring to Figure 1 and Figure 2, the mammography system 12 further includes a compression paddle or plate 28 and a support structure 30 to which one or more of the radiation source 16, the radiation detector 18, and / or the compression plate 28 are mounted. In an embodiment, the mammography system 12 may further include a controller 32. The controller 32 may be a workstation having at least one processor / central processing unit / computer and a memory device / database storing information and / or instructions employed by the controller 32 for the operation of the system 10, as Figure 1 shown, or in other embodiments, the controller 32 may be embedded / integrated into one or more of the various components of the mammography system 12 disclosed above. In an embodiment, the controller 32 may be in electrical communication with the radiation source 16, the radiation detector 18, and / or the compression plate 28 via a cable 34. As will be appreciated, in an embodiment, the connection 34 may be a wireless connection. In an embodiment, the controller 32 may include a radiation shield 36 that protects an operator of the mammography system 12 from the radiation rays 22 emitted by the radiation source 16. The controller 32 may also include a display 38, a keyboard 40, a mouse 42, and / or other suitable user input devices that facilitate controlling the system 10 via a user interface 44.

[0035] As Figure 1 and Figure 2 further shown, the radiation source 16 and the radiation detector 18 together form part of an X-ray system that provides an X-ray image for the purpose of imaging a body part of a patient, such as the breast 52. As described above, the radiation source 16 emits radiation rays 22 such that the radiation rays 22 travel from the radiation source 16 to the radiation detector 18. Although the radiation rays 22 are discussed herein as X-rays, it should be understood that the radiation source 16 may emit other types of electromagnetic rays that can be used to image a patient. The radiation source 16 may be mounted to the support structure 30 such that the radiation source can rotate about an axis 46 relative to the radiation detector 18, but movement of the radiation source 16 in a path other than rotation about a fixed axis, such as during digital breast tomosynthesis (DBT), is also contemplated. In an embodiment, the radiation detector 18 may be configured to rotate or translate within its housing, such as in the directions indicated by arrows 53 and 55.

[0036] In Figure 1In the illustrated exemplary embodiments, the radiation source 16 and the detector 18 are mounted to a gantry 90 that is fastened to a support structure 30. The support structure 30 houses a translation mechanism 92 that is operatively connected to the gantry 90. The translation mechanism 92 is operable to vertically move the gantry 90 relative to the support structure 30 to position the gantry 90 at an appropriate height to accommodate the size of a patient on which the mammography system 12 is utilized. The translation mechanism 92 is also operable to rotate the gantry 90 about a horizontal axis 46 relative to the support structure 30 to rotationally position the gantry 90 relative to the patient as needed.

[0037] The gantry 90 includes a generally C-shaped body 94 with the radiation source 16 at one end and the detector 18 at the opposite end. In this configuration, regardless of the vertical and / or rotational orientation of the gantry 90, such as positioning the radiation source 16 and the detector 18 relative to the patient's breast 52 to obtain X-ray images in various orientations, such as for cranio-caudal (CC), mediolateral oblique (MLO), or mediolateral (ML) / lateromedial (LM) views, etc., the radiation source 16 is set in the desired alignment relative to the detector 18. In this position, the detector 18 is capable of receiving X-rays 22 emitted from the radiation source 16 that pass through the patient portion, i.e., the patient's breast 52, located between the radiation source 16 and the detector 18, so as to generate image data to be sent to the control system 32 of the mammography device / system 10 to create / reconstruct 2D and / or 3D images or image datasets for a physician to view (such as by using DBT), as well as other known methods.

[0038] Additionally, in another embodiment, the radiation source 16 can be attached to the gantry 90 to rotate and / or move independently of the gantry 90 and the detector 18 so that the radiation source 16 can take X-ray images of a patient's breast at various angles (e.g., between + / −90°) relative to the detector 18. When operating the mammography system 12 in a screening imaging procedure or imaging mode or in a diagnostic imaging procedure or imaging mode (e.g., in one or more of spot compression (SPOT), magnification (MAG), or biopsy imaging procedures or imaging modes), the images obtained for the radiation source 16 between these angles can be used to create 2D and / or 3D images.

[0039] As described above, the radiation detector 18 receives the radiation rays 22 emitted by the radiation source 16. In an embodiment, data regarding the radiation rays 22 received by the radiation detector 18 can be telecommunicated electrically from the radiation detector 18 to the controller 32 via a cable / electrical connection 34 such that the controller 32 generates one or more 2D and / or 3D images that can be displayed on the display 38 and stored in a memory device.

[0040] The compression plate 28 is operably movable toward and away from the radiation detector 18 in response to instructions from the controller 32 or in response to instructions from a controller such as a remote control 84 on or near the mammography system 10 or a switch controller 80 connected by a cable 82, as indicated by the arrow / compression axis 48, such that the compression plate 28 flattens and holds in place a body part (e.g., the breast 52) against the surface 50 of the radiation detector 18. In this regard, the radiation detector 18 and particularly its surface 50 are referred to herein as the "compression surface or support plate", which cooperates with the compression plate 28 to compress and clamp the patient's breast therebetween.

[0041] Now referring to Figure 3 , in an exemplary embodiment of the present disclosure, the biopsy device 110 is attached to the mammography system 12 by known means, such as to the gantry 90. The biopsy device 110 is provided to allow the mammography system 12 to perform diagnostic biopsy procedures, e.g., where the movement of the biopsy device 110 is guided by an image of the breast 52 obtained by the mammography imaging system 12. Additionally, with regard to Figure 4 another exemplary embodiment shown, a magstand 112 may be positioned on the surface 50 to position the breast 52 engaged thereon closer to the radiation source 16. Positioning the breast 52 closer to the radiation source 16 on the magstand 112 enables the mammography system 12 to obtain a magnified image of the breast 52 in a diagnostic MAG imaging mode for the mammography imaging system 12.

[0042] To facilitate the use of the mammography imaging system 12 to perform Figure 3 and Figure 4 the diagnostic imaging procedures in the configurations shown, as Figure 5 shown, the mammography imaging system 12 includes a control device 304, which is shown as part of the controller 32 and includes a control processor 306, an electronic memory 308 for storing the operating instructions of the control processor 306 and other information. However, embodiments where the control device 304 and / or the control processor 306 are separate from other control devices are also covered in the present disclosure, such other control devices being, for example, the controller 32 or other control circuitry local or remote to the mammography imaging system 12, such that the functions of the control device 304 may be performed in part by the controller 32 or separately therefrom, depending on the circumstances.

[0043] The control processor 306 can command the operation of the mammography imaging system 12 to perform filtering, inspection, and / or calibration protocols, and can process the acquired data. Relative to the radiation source 16, the control device 304, optionally in cooperation with the controller 32, provides power, focal position, control signals, etc. for the X-ray inspection sequence. According to certain embodiments, the control device 304 can control the operation of the gantry 90 (or other structural support to which the radiation source 16 and the detector 18 are attached), and / or the translation and / or tilt of the patient support during the inspection.

[0044] In addition, as Figure 5 illustrated in the exemplary embodiments, via the motor controller 336, the control processor 306 can control the operation of the linear positioning subsystem 332 and / or the rotational subsystem 334 for moving components of the mammography imaging system 12. The control processor 306 can include signal processing circuitry and an associated memory circuitry, such as the electronic memory 308. In such embodiments, the memory circuitry 308 can store programs, routines, and / or encoded algorithms executed by the control processor 306 to operate the mammography imaging system 12 (including the X-ray source 16) and to process the digital measurements acquired by the detector 18 according to the steps and processes discussed herein. In one embodiment, the control processor 306 can be implemented as all or part of a processor-based system.

[0045] The radiation source 16 can be controlled by an X-ray controller 338 included within the control processor 306. The X-ray controller 338 can be configured to provide power, timing signals, and / or focal size and focal position to the radiation source 16. In addition, in some embodiments, the X-ray controller 338 can be configured to selectively activate the radiation source 16 such that tubes or emitters at different locations within the mammography imaging system 12 can operate synchronously with each other or independently of each other, or switch the source between different energy distributions during the imaging phase.

[0046] The control processor 306 may include a data acquisition system (DAS) 340. The DAS 340 receives data collected by the readout electronics of the detector 18, such as digital signals from the detector 18. Then, the DAS 340 may convert and / or process the data for subsequent processing by a processor-based system, such as a computer 342 operatively connected to the control processor 306. In certain specific implementations discussed herein, the circuitry within the detector 18 may cause the analog signals of the detector to be converted to digital signals before being sent to the data acquisition system 340. The computer 342 may include or communicate with one or more non-transitory memory devices 308 that are capable of storing data to be processed by the computer 342, data to be processed by the computer 342, or instructions to be executed by the image processing circuitry 344 of the computer 342. For example, the processor of the computer 342 may execute one or more instruction sets stored on the memory 308, which may be the memory of the control device 304 or the computer 342, other memory of the processor, firmware, or similar instances, to perform image acquisition and reconstruction techniques and / or processes.

[0047] The computer 342 may also be adapted to control features enabled by the control processor 306 (i.e., scan operations and data acquisition), such as in response to commands and scan parameters provided by an operator via the user interface 310 and / or the operator workstation 348. Additionally, the display 44 / 350 and / or printer 352 coupled to the control device 304 and the user interface 310 allow the operator to view relevant system data, imaging parameters, raw imaging data, reconstructed data (e.g., soft tissue images, bone images, segmented vascular trees, etc.), material basis images, and / or material decomposition results, etc. Further, the control processor 306 may include or be coupled to a memory or a Picture Archiving and Communication System (PACS) 354. The PACS 354 may be directly coupled to the computer 342 and / or coupled to a remote system or client 356, a Radiology Information System (RIS), a Hospital Information System (HIS), or an internal or external network, such that image data can be accessed by others at different locations.

[0048] In Figure 5 and Figure 6In an exemplary implementation of the operation of the mammography imaging system 12 and method, to enhance the ability of the mammography imaging system 12 to perform a diagnostic imaging procedure after one or more screening imaging procedures performed using the mammography imaging system 12 and / or a separate medical imaging system, one or more of the controller 32, the control processor 306, and / or the image processing circuitry 344 in the computer 342 may include artificial intelligence (AI) and / or machine learning (ML) algorithms that form an image prediction module 380. The image prediction module is trained to analyze one or more previous screening images 382 of the breast 52 stored in the PACS 354 and is configured to generate one or more predicted views 384 of the breast 52 on the mammography imaging system 12. The one or more predicted views are utilized when performing a subsequent diagnostic imaging procedure of the breast 52. The subsequent diagnostic imaging procedure may be defined as an imaging procedure performed after a screening procedure and focused on obtaining any local views or images of one or more ROIs 386 identified within the breast 52 in the images from the screening imaging procedure. The image prediction module 380 operates to examine one or more previous screening images 382 provided as input to the image prediction module 380 to create an artificial or synthetic image 385 of the breast 52 as a predicted view 384 at a location optimized for imaging of the ROI 386 identified within the screening image 382. The predicted view represents an image view of the breast 52 obtained when performing the diagnostic imaging procedure.

[0049] In an exemplary embodiment, after creating the prior screening image 382 and optionally storing it in the PACS 354, one or more mammographic images of a breast 52 (including but not limited to the CC image 400 and / or the MLO image 402) or images of the breast 52 from other imaging modalities (such as ultrasound (US) images, magnetic resonance (MRI) images, or other types of imaging modalities), the image prediction module 380 operates to generate a predicted or synthetic ML or LM view 385 of the breast 52 that is similar to the view obtained using the prior screening image 382 in a subsequent diagnostic imaging procedure. The synthetic ML or LM view 385 generated by the image prediction module 380 provides a representation of the correct orientation or position of the breast 52 on the mammography imaging system 12 so as to set the ROI 386 (e.g., microcalcifications, cysts, solid masses, etc.) identified within the prior screening image 382 or other clinically relevant regions present within the prior screening image 382 in the optimal position for imaging of the ROI 386 in the view obtained in the subsequent diagnostic imaging procedure. For example, traditional image processing techniques or artificial intelligence (AI)-based methods (including machine learning (MaL) and deep learning (DL), etc.) or a combination of both can be used to create the synthetic ML and / or LM views 385 of the breast 52 from the prior screening image 382. For AI-based identification methods, the final goal of identifying the ROI 386 in the prior screening image 382 and forming the synthetic ML and / or LM views 385 can be formulated as an image segmentation or object localization problem. Although MaL-based methods (such as support vector machines (SVM), random forests (RF), etc.) can be used to solve these problems, generating a deep learning model (e.g., a convolutional neural network (CNN) (a type of DL-based model)) is most suitable for such tasks, resulting in better accuracy and adaptability under various imaging conditions. Additionally, leveraging the identification and localization of the ROI 386 and other markers (such as the nipple 394( Figure 9 )) present within the prior screening image 382 by the image prediction module 380, the image prediction module 380 can output results, such as the predicted view 384, including but not limited to the synthetic ML and / or LM views 385 of the breast 52, together with an optional visual indication 387( Figure 9 ) on the synthetic ML / LM view 385 of the position of the ROI 386 to assist in positioning the breast 52 on the mammography imaging system 12 for a subsequent diagnostic imaging procedure.

[0050] Regarding an exemplary form of the image prediction module 380, the image prediction module 380 can be part of a DL / image processing algorithm pipeline, where initial image processing performed in the image processing circuitry 344 detects the nipple 394( Figure 9 ) and the skin line 396( Figure 9) The image prediction module 380 utilizes these localization features in the previous screening image 382 for predicting the geometric image 392 ( Figure 9 ) and / or the synthetic radiography view 390 ( Figure 8 ). Additionally, regarding the training of the image prediction module 380 for the generation of an image for one predicted view 384 or predicted views, the image prediction module 380 can be provided with a set of CC / MLO images of the breast or other body part and images of the same breast using other imaging modalities (e.g., US, MRI, etc.) as inputs for comparison with the desired views of the breast (e.g., ML and / or LM views), thereby forming a ground truth for comparing the output images or views from the image prediction module 380.

[0051] Specifically referring to Figure 6 , in an exemplary implementation of the method 600 for the operation of the image prediction module 380, initially in step 602, one or more previous screening images 382 are retrieved from an electronic storage device or memory (such as PACS 354). In step 604, the one or more previous screening images 382 are provided as inputs to the image prediction module 380. The processes of retrieving and providing the previous screening images 382 as inputs in steps 602 and 604 can be automatically performed by the controller 32, the control processor 306, and / or the image processing circuitry 344 (such as immediately when the screening imaging procedure is completed using the mammography imaging system 12) or can be performed manually. In an exemplary implementation of the manual operation of providing the previous screening images 382 to the image prediction module 380, as Figure 7 shown, after being acquired or retrieved from the mammography imaging system 12, the previous screening images 382 can be presented on the display 44 / 350 together with an icon 388 representing the activation of the image prediction module 380 on the display 44 / 350. When the icon 388 for manual retrieval is selected (such as by selecting the icon 388 using the user interfaces 40, 42) or when the retrieval is automatically initiated, the previous screening images 382 are retrieved from the memory 308 and / or PACS 354 and supplied or provided to the image prediction module 380. In addition to the previous screening images 382, the input 604 can include information on the operating parameters of the mammography imaging system 12 when the previous screening images 382 were obtained, such as the field of view (FoV) and compression force, the metadata of the previous screening images 382 (including the angles of the previous screening images 382, e.g., CC images and MLO images of one or both of the right and left breasts 52), and the lesion location information manually added to the previous screening images 382 or provided by a computer-aided detection (CAD) system associated with the mammography imaging system 12.

[0052] When one or more prior screening images 382 are received, the image prediction module 380 automatically continues, for example, to generate in step 606 a predicted view 384 of the breast 52 or other body part represented in the prior screening image 382, which is provided as an output from the image prediction module 380 in step 608. As Figure 8 exemplified by the exemplary embodiments of, the output 608 of the predicted view 384 may take the form of an actual predicted radiographic image 390 of the body part (e.g., breast 52) to be obtained in a subsequent diagnostic imaging procedure, or may be a Figure 9 generalized geometric image 392 as shown. With the predicted radiographic image 390, the representation of the breast 52 corresponds to the actual predicted radiographic view of the selected image of the breast 52, which will be obtained by the mammography imaging system 12 in a subsequent diagnostic imaging procedure, such as an ML or LM image. The geometric image 392 provides a generalized representation of the breast 52, which at least includes the ROI 386, the nipple 394, the skin line representation 396, and the pectoral muscle 398.

[0053] In either form, the predicted view 384 can be presented to the user on the display 44 / 350 in association with the prior screening image 382 so as to review the information provided in each of the predicted view 384 and the prior screening image 382. The predicted view 384 and the prior screening image 382 can be presented to the user, optionally nipple-aligned with each other, to facilitate reviewing the correspondence between the predicted view 384 and the prior screening image 382 and the correct positioning of the patient on the mammography imaging system 12 for performing a diagnostic imaging procedure, such as a biopsy for a MAG procedure.

[0054] Now referring to Figure 10, in another exemplary embodiment of method 700 of the operation of image prediction module 380, at step 702, prior to performing a diagnostic imaging procedure on a patient, a prefetch image retrieval request is issued from the worklist or schedule of patient 703 to access previously screened images 382 stored in association with the patient file, such as images stored in memory device 308 and / or PACS 354. At step 702, previously screened images 382 from any image modality associated with the selected patient are accessed and provided as input to image prediction module 380. At step 704, image prediction module 380 operates to generate one or more predicted views 384 of a body part of the patient, the body part of the patient that will be the subject of a subsequent diagnostic imaging procedure. At step 706, one or more predicted views 384 are provided as output 707 from module 380 and stored in database 708. When the patient associated with predicted views 384 is preparing for a diagnostic imaging procedure, the predicted views 384 can be accessed by a user of the radiography imaging system 10 from database 708, optionally together with previously screened images 382, for review on display 44 / 350 to properly position the patient on the radiography imaging system 10 prior to initiating a subsequent diagnostic imaging procedure on the patient for imaging of ROI 386.

[0055] It should be understood that the foregoing apparatus and methods of the present disclosure are not limited to specific embodiments and methods as these may vary. It should also be understood that the terms used herein are for the purpose of describing particular exemplary embodiments only and are not intended to limit the scope of the present disclosure, which will be limited only by the appended claims.

Claims

1. A radiographic imaging system (10) adapted to provide patient positioning assistance when performing a diagnostic imaging procedure, the radiographic imaging system (10) comprising: a. Radiation source (16); b. a detector (18) adapted to receive radiation (22) emitted from the radiation source (16) to generate image data; c. a controller (32 / 304) operably connected to the radiation source (16) and the detector (18) to control the operation of the radiation source (16) and the detector (18) to generate the image data, the controller (32 / 304) comprising a central processing unit (342) and an interconnected electronic storage unit (308) for processing the image data from the detector (18); d. a display (38 / 350) operably connected to the controller (32 / 304) for presenting an image formed from the image data; e. a user interface (40 / 348) operably connected to the controller (32 / 304) to enable user input to the controller (32 / 304); and f. an image prediction module (380), the image prediction module being operably connected to the controller (32 / 304) and configured to:

1. Receive one or more previous screening images of the patient (382); and 2. Generating a predicted view (384) of the patient for presentation on the display (38 / 350).

2. The radiographic imaging system (10) of claim 1, wherein the prior screening images (382) include images from one or more imaging modalities.

3. The X-ray radiographic imaging system (10) of claim 1, wherein the previous screening image (382) includes at least one of an annotation of the previous screening image (382) and metadata of the previous screening image (382).

4. The radiographic imaging system (10) of claim 1, wherein the predicted view (384) is a predicted radiographic image (390) of the patient.

5. The radiographic imaging system (10) of claim 1, wherein the predicted view (384) is a predicted geometric image (392) of the patient.

6. The X-ray radiographic imaging system (10) of claim 1, wherein the previous screening image (382) includes at least one of a craniocaudal (CC) image (400) of the patient or a mediolateral oblique (MLO) image (402) of the patient.

7. The X-ray radiographic imaging system (10) of claim 6, wherein the predicted view (384) includes at least one of a middle-lateral (ML) view (385) of the patient or a lateral-medial (LM) view (385) of the patient.

8. The radiographic imaging system (10) of claim 6, wherein the radiographic imaging system (10) is a mammographic imaging system (12).

9. The x-ray radiographic imaging system (10) of claim 8, further comprising a biopsy device (110) operably connected to the mammographic imaging system (10) to perform a diagnostic imaging procedure.

10. The radiographic imaging system (10) of claim 8, further comprising a magnification support (112) operably connected to the mammographic imaging system (10) to perform a diagnostic imaging procedure.

11. The X-ray radiographic imaging system (10) of claim 1, wherein the image prediction module (380) is formed by artificial intelligence.

12. A method for providing patient positioning assistance for performing a diagnostic imaging procedure on a radiographic imaging system (10), the method comprising the steps of: a. Providing an X-ray imaging system (10), the X-ray imaging system comprising: i. Radiation source (16); ii. Detector (18); iii. a controller (32 / 304) operably connected to the radiation source (16) and the detector (18) to control the operation of the radiation source (16) and the detector (18) to generate image data, the controller (32 / 304) comprising a central processing unit (342) and an interconnected electronic storage unit (308), for processing the image data from the detector (18); iv. a display (38 / 350) operatively connected to the controller (32 / 304) for presenting an image formed from the image data; v. a user interface (40 / 348) operably connected to the controller (32 / 304) to enable user input to the controller (32 / 304); and vi. an image prediction module (380) operably connected to the controller (32 / 304) and configured to generate a predicted view (384) of the patient from one or more previous screening images (382) of the patient for presentation on the display (38 / 350); b. supplying the one or more previous screening images (382) to the image prediction module (380); c. generating the predicted view of the patient (384); and d. Presenting the predicted view (384) of the patient on the display (38 / 350).

13. The method of claim 12, wherein the step of supplying the one or more previous screening images (382) to the image prediction module (380) includes supplying at least one of a cranio-caudal (CC) image (400) of the patient and a mediolateral oblique (MLO) image (402) of the patient.

14. The method of claim 12, wherein the step of generating the predicted view (384) of the patient comprises generating at least one of a mediolateral (ML) view (385) of the patient or a lateral middle (LM) view (385) of the patient.

15. The method according to claim 12, further comprising the steps of: a. positioning the patient on the X-ray imaging system (10) according to the predicted view (384); and b. performing a diagnostic imaging procedure on the patient.

Images