DESC:The following specification particularly describes and ascertains the nature of this invention and the manner in which it is to be performed:-

This application is based on and derives the benefit of Indian Provisional Application 4395/CHE/2015, the contents of which are incorporated herein by reference.
TECHNICAL FIELD
[001] The embodiments herein generally relate to the field of medical imaging systems and more particularly to calibration of medical imaging systems.

BACKGROUND
[002] Modern diagnostic medicine has benefited significantly from medical imaging systems that enable generating images of internal and/or external body structures of a subject under observation. To capture images of intended body parts of the subject, conventionally, a user of a medical imaging system is required to perform initial acquisition set up or calibration manually based on inputs of a target area (patient acquisition area) derived from manual observation.
[003] Efforts to provide higher level of automation for calibration of medical imaging systems are important. Automation for image acquisition set up reduces time consumed for initial set up, time consumed per subject (patient) and effectively increases patient throughput. The automation can be brought in by an imaging device assisted medical imaging system that may provide the user, such as a field engineer or physician, with visual feedback (still image or video) of the acquisition setup with reference to the patient acquisition area of interest for calibrating the medical imaging system. However, existing visual feedback are independent systems without any integration or direct coupling with the medical imaging system to be calibrated.

OBJECT OF INVENTION
[004] The principal object of the embodiments herein is to provide methods and systems for visual feedback based calibration of a medical imaging system by projecting one or more key points of a target area (real world) of the medical imaging system as an overlay on the visual feedback frame of the target area captured by an imaging device of a visual feedback system and are aligned with one or more key points of the target area located in the visual feedback frame.
[005] Another object of the embodiments herein is to provide methods and systems for improving calibration accuracy of the medical imaging system by minimizing difference between one or more projected key points and one or more located key points on the visual feedback frame below a predefined threshold during the alignment, wherein the difference is minimized based on an iterative error correction mechanism.

SUMMARY
[006] In view of the foregoing, an embodiment herein provides a method for visual feedback based calibration of a medical imaging system. The method comprises capturing an image of a target area and locating at least one key point present in the target area on a visual feedback frame of the captured image by determining frame coordinates for the at least one key point based on an image data set. Further, the method comprises projecting the at least one key point of the target area as an overlay on the visual feedback frame using a mapping mechanism and the image data set. The mapping mechanism converts real world coordinates of the at least on key point of the target area to frame coordinates of the visual feedback frame. Furthermore, the method comprises performing calibration of the medical imaging system by applying an iterative error correction mechanism to minimize difference between the at least one projected key point and the at least one located key point on the visual feedback frame below a predefined threshold.
[007] Embodiments further disclose a visual feedback system for visual feedback based calibration of a medical imaging system. The visual feedback system comprises a calibration module configured to capture an image of a target area and locating at least one key point present in the target area on a visual feedback frame of the captured image by determining frame coordinates for the at least one key point based on an image data set. Further, the calibration module is configured to project the at least one key point of the target area as an overlay on the visual feedback frame using a mapping mechanism and the image data set. The mapping mechanism converts real world coordinates of the at least on key point of the target area to frame coordinates of the visual feedback frame. Furthermore, the calibration module is configured to perform calibration of the medical imaging system by applying an iterative error correction mechanism to minimize difference between the at least one projected key point and the at least one located key point on the visual feedback frame below a predefined threshold. These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.

BRIEF DESCRIPTION OF FIGURES
[008] The embodiments of this invention are illustrated in the accompanying drawings, throughout which like reference letters indicate corresponding parts in the various figures. The embodiments herein will be better understood from the following description with reference to the drawings, in which:
[009] FIG. 1 illustrates an example system comprising a medical imaging system assisted by a visual feedback system for visual feedback based calibration of the medical imaging system, according to embodiments as disclosed herein;
[0010] FIG. 2 illustrates a plurality of components of the visual feedback system, according to embodiments as disclosed herein;
[0011] FIG. 3 is a flow diagram illustrating a method for visual feedback based calibration of the medical imaging system, according to embodiments as disclosed herein;
[0012] FIG. 4 is a flow diagram illustrating a method for projecting one or more key points of a target area in the medical imaging system as an overlay on the visual feedback frame of the target area captured by an imaging device, according to embodiments as disclosed herein;
[0013] FIGs. 5a, 5b and 5c illustrate video feed back frames used for calibration, according to embodiments as disclosed herein; and
[0014] FIGs. 6a and 6b illustrate video feed back frames with no estimated error correction and estimated error correction respectively, according to embodiments as disclosed herein.

DETAILED DESCRIPTION
[0015] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
[0016] The embodiments herein achieve methods and systems for visual feedback based calibration of a medical imaging system. A method includes projecting one or more key points of a target area (real world) of the medical imaging system as an overlay on the visual feedback frame, wherein the visual feedback frame is an image of the target area captured by an imaging device of a visual feedback system. One or more key points of the target area are then located on the visual feedback frame. Further, the method includes calibrating accuracy of the medical imaging system by minimizing difference between one or more projected key points (overlay) and one or more located key points on the visual feedback frame below a predefined threshold. The difference or the error in mapping of real world coordinates of the key points to frame coordinates of the visual feedback frame is minimized based on an iterative error correction mechanism.
[0017] In an embodiment, the imaging device can be a camera installed as independent element of the visual feedback system or can be integrated into the medical imaging system or can be any other imaging sensor capable of capturing target images and providing it to the visual feedback system for the calibration.
[0018] In an embodiment, the medical imaging system can be a X-ray imaging system, a Computed Tomography (CT) or any other medical imaging system
[0019] Embodiments herein enable automation of the medical imaging systems, for example X-ray imaging system, for image acquisition planning process for diagnostic studies, thereby increasing patient throughput.
[0020] Referring now to the drawings, and more particularly to FIGS. 1 through 6, where similar reference characters denote corresponding features consistently throughout the figures, there are shown embodiments.
[0021] FIG. 1 illustrates an example system comprising a medical imaging system 100 assisted by a visual feedback system 102 for visual feedback based calibration of the medical imaging system 100, according to embodiments as disclosed herein.
[0022] In the example here, the medical imaging system 100 is X-ray imaging system with a collimator end and a detector end. At the collimator end, a collimator 110 supported by a collimator support 112 acts as a source for X-ray to be incident on a subject, for example the patient, present at a target area 114 (detector). The target area 114 may be at one of the detector set up such as detector support 116a or 116b respectively. A user console 122a, at the collimator end, provides a User Interface (UI) for the user (for example field engineer, physician or the like) with a plurality of controls for capturing subject’s images using the medical imaging system 100.
[0023] The embodiments herein provide the visual feedback system 102 assisting the medical imaging system 100 by providing automation for image acquisition set up or calibration of the medical imaging system 100. The visual feedback system 102 a calibration module 106 that can be configured to calibrate the medical imaging system 100 for image acquisition set up using an imaging device 104, a user console 122b and a display screen 108. The user console 122b provides a User Interface (UI) for the user (for example field engineer, physician or the like) during calibration of the medical imaging system 100.
[0024] To calibrate the medical imaging system 100 with assistance from the visual feedback system 102, the calibration module 106 can be configured to generate an image data set of the target area 114, wherein the target area 114 lies within Field of Vision (FoV) 120 of the imaging device 104. The image data set can be generated by capturing a plurality of images of the target area 114 by placing a pre-defined target pattern on the target area, wherein position of the target area 114 and distance between the target area 114 and the imaging device 104 is varied for each captured image. Further, for the image data set, a plurality of reference key points are identified on the pre-defined target pattern. Thereafter, corresponding meta data associated with the reference key points such as real world coordinates or 3D coordinates, frame coordinates and the like is determined and stored. The image data set and the metadata are made available for further analysis for calibration of the medical imaging system 100. The real world coordinates of the reference points can be obtained from a mechanical control module 118 of the medical imaging system. The mechanical control module 118 also controls positioning of the collimator support, positioning of the target area 114 placed at the detector support 116a or 116b respectively and positioning of the user console 122b.
[0025] Once the image data set is generated, the calibration module 106 can be configured to capture an image of the target area 114, referred as a visual feedback frame, to locate one or more key points of the target area 114 (real world) on a visual feedback frame of the captured image, which can be displayed on the display screen 108 for the user. The image data set is used to locate one or more key points on the visual feedback frame to identify feedback frame coordinates for the key points (located key points) using the image data set. For example, a crosshair can be a key point for the X-ray imaging system as in example of FIG. 5. In another example, corners points of target projection area can be the key points to be projected as an overlay on the visual feedback frame as in example of FIG. 6.
[0026] Once the frame coordinates of one or more key points are identified (when key points are located on the feedback frame), the calibration module 106 can be configured to project one or more key points of the target area 114 as an overlay on the visual feedback frame, displayed on the display screen 108, using a mapping mechanism and the image data set. The mapping mechanism, explained in conjunction with FIG. 4, converts real world coordinates of one or more key points of the target area 114 to coordinates of the feedback frame displayed on the display screen 108. Further, the calibration module 106 can be configured to calibrate the medical imaging system 102 by comparing the located key points and the projected key points for alignment or overlap. Maximum overlap provides maximum calibration accuracy, which can be obtained by minimizing difference (minimizing error) between one or more projected key points and corresponding one or more located key points located on the feedback frame. The minimization is carried out using the iterative error correction mechanism so as to reduce the error in mapping of the real world coordinates of the key points to the frame coordinates of the key points. The iterative error correction mechanism minimizes difference between the at least one projected key point and the at least one located key point on the visual feedback frame by estimating parameters of an error function, wherein the error function is a function of position of the imaging device and position of the at least one projected key point. Once the error is reduced below a predefined threshold, the desired accuracy can be said to be achieved. The proximity of projected key points and the located key points on the visual feedback frame enable the user to observe whether the calibration is achieved or not.
[0027] Once the medical imaging system 102 is calibrated using the calibration module, the medical imaging system 102 can then be used to measure a source to object distance (for example, patient to collimator distance), hence providing automation in radiation dose delivered to the patient. Further, the calibrated imaging system 102 can be used to improve the accuracy of dose delivered to the patient by providing fine adjustments to an imaging collimation area.
[0028] Embodiments herein enable projecting patient, detector and collimator planes on the plane of the media. In an example herein, embodiments herein can be used for calibrating a camera for adjusting a collimation region, wherein the camera serves as an interface to the medical imaging system. In an example herein, embodiments herein can be used for calibrating a camera for determining a stitching range and number of shots to be captured for a procedure, wherein the camera serves as an interface to a medical imaging system
[0029] FIG. 2 illustrates a plurality of components of the visual feedback system 102, according to embodiments as disclosed herein.
[0030] Referring to figure 2, the visual feedback system device 102 is illustrated in accordance with an embodiment of the present subject matter. In an embodiment, the visual feedback system102 may include a processor 202, an input/output (I/O) interface 204 (herein a configurable user interface), and a memory module 206. The I/O interface 204 may include, for example, a web interface, a graphical user interface such as the display screen 108, the user console 122b and the like. The I/O interface 204 may allow the visual feedback system 102 to communicate with other systems and devices such as the mechanical control module 118 of the medical imaging system wired network, Wi-Fi networks, and device to device communication and so on. The memory module 206 maintains the image data set. Further, the visual feedback system 102 comprises a calibration module 106 configured to perform steps as described in FIG. 1 and not repeated for brevity.
[0031] FIG. 3 is a flow diagram illustrating a method for visual feedback based calibration of the medical imaging system 100, according to embodiments as disclosed herein.
[0032] To calibrate the medical imaging system 100 assisted by the visual feedback system 102, at step 302, the method 300 includes allowing the calibration module 106 to generate the image data set of the target area 114 lying within the Field of Vision (FoV) 120 of the imaging device 104. The image data set can be generated by capturing the plurality of images of the target area 114 by placing the pre-defined target pattern on the target area, wherein position of the target area 114 and distance between the target area 114 and the imaging device 104 is varied for each captured image. Further, for the image data set, the plurality of reference key points are identified on the pre-defined target pattern. Thereafter, corresponding meta data associated with the reference key points such as real world coordinates or 3D coordinates, frame coordinates and the like is determined, stored. The image data set and the metadata is made available for further analysis for calibration of the medical imaging system 100. The real world coordinates of the reference points can be obtained from a mechanical control module 118 of the medical imaging system.
[0033] Once the image data set is generated, at step 304, the method 300 allows the calibration module 106 to capture the image of the target area 114 (visual feedback frame) to locate one or more key points of the target area 114 (real world) on the visual feedback frame of the captured image, which can be displayed on the display screen 108. The image data set is used to locate one or more key points on the visual feedback frame to identify feedback frame coordinates (for example, 2D coordinates) for the key point using the image data set. For example, the crosshair can be one of the key points in the X-ray imaging system.
[0034] Once the frame coordinates of one or more key points are identified, at step 306, the method 300 allows the calibration module 106 to project one or more key points of the target area 114 as an overlay on the visual feedback frame, displayed on the display screen 108, using a mapping mechanism and the image data set. The mapping mechanism, explained in conjunction with FIG. 4, converts real world coordinates of one or more key points of the target area 114 to coordinates of the feedback frame displayed on the display screen 108. The mapping mechanism is explained in conjunction with FIG. 4.
[0035] Further, at step 308, 310 and 312 the method 300 allows the calibration module 106 to perform calibration of the medical imaging system 102 by applying the iterative error correction mechanism that minimizes difference between one or more projected key points and corresponding one or more key points located on the feedback frame. The minimization is carried out using the iterative error correction mechanism so as to reduce the error in mapping mechanism during mapping of real world coordinates to frame coordinates for the calibration. The iterative error correction mechanism minimizes difference between the at least one projected key point and the at least one located key point on the visual feedback frame by estimating parameters of the error function, wherein the error function is the function of position of the imaging device and position of the at least one projected key point. The calibration is said to be complete when the error falls below the predefined threshold and provide calibration accuracy is said to be achieved. Once the error is reduced below the predefined threshold, at step 314, the method 300 allows the calibration module 106 to terminate the calibration and confirm completion and validation of calibration of the medical imaging system 100.
[0036] The various actions in method 300 may be performed in the order presented, in a different order or simultaneously. Further, in some embodiments, some actions listed in FIG. 3 may be omitted.
[0037] FIG. 4 is a flow diagram illustrating a method 400 for projecting one or more key points of the target area 114 in the medical imaging system 102 as the overlay on the visual feedback frame of the target area 114 captured by the imaging device 104, according to embodiments as disclosed herein. At step 402, the method 400 includes allowing the calibration module 106 to compute a device matrix corresponding to a plurality of intrinsic parameters of the imaging device 104. At step 404, the method 400 includes allowing the calibration module 106 to derive a transformation matrix using the device matrix and frame coordinates of the plurality of reference key points from the image data set. At step 406, the method 400 includes allowing the calibration module 106 to project one or more key points of the target area for a as overlay on the visual feedback frame of the same target area using the transformation matrix. The various actions in method 400 may be performed in the order presented, in a different order or simultaneously. Further, in some embodiments, some actions listed in FIG. 4 may be omitted.
[0038] FIGs. 5a, 5b and 5c illustrate video feed back frames used during calibration, according to embodiments as disclosed herein. The FIG. 5a depicts a visual feedback frame 502 captured by the FoV 120 of the imaging device 104. The visual feedback frame depicts the captured target area 114 with a pre-defined pattern 504 for generating the image data set. A key point 506 (cross hair) of the target area 114 is depicted in FIG. 5b and upon calibration crosshair 506 and a projected key point 508 (overlay using mapping mechanism) are seen overlapping each other indicating completion of calibration.
[0039] FIGs. 6a and 6b illustrate video feed back frames with no estimated error correction and estimated error correction respectively, according to embodiments as disclosed herein.FIG. 6a illustrates a projection on the target area 602 and a corresponding rectangular overlay 602 projected on the visual feedback screen that requires a correction. The FIG. 6b illustrates the visual feedback frame after the projection correction 606 is applied that reduces the error between the actual projection and the overlay.
[0040] The embodiments disclosed herein can be implemented through at least one software program running on at least one hardware device and performing network management functions to control the network elements. The network elements shown in FIG. 1 through FIG. 6 include blocks which can be at least one of a hardware device, or a combination of hardware device and software module.
[0041] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.
,CLAIMS:We claim:

1. A method for visual feedback based calibration of a medical imaging system, the method comprises:
capturing an image of a target area of the medical imaging system;
locating at least one key point present in the target area on a visual feedback frame of the captured image by determining frame coordinates for the at least one key point based on an image data set;
projecting the at least one key point of the target area as an overlay on the visual feedback frame using a mapping mechanism and the image data set, wherein the mapping mechanism converts real world coordinates of the at least on key point of the target area to frame coordinates of the visual feedback frame; and
performing calibration of the medical imaging system by applying an iterative error correction mechanism to minimize difference between the at least one projected key point and the at least one located key point on the visual feedback frame below a predefined threshold.
2. The method as claimed in claim 1, wherein the image data set is generated by:
capturing a plurality of images of the target area by placing a pre-defined target pattern on the target area, wherein position of the target area and distance between the target area and the imaging device is varied for each captured image;
identifying a plurality of reference key points on the target to determine corresponding plurality of frame coordinates for the plurality of reference key points of the target area, wherein the frame coordinates for the plurality of reference points are derived from real world coordinates of the plurality of reference points that are received from the mechanical control module of the medical imaging system; and
storing the captured plurality of images along with meta data and frame co-ordinates of the plurality of reference key points of the target area.
3. The method as claimed in claim 1, wherein the mapping mechanism comprises:
computing a device matrix corresponding to a plurality of intrinsic parameters of the imaging device; and
deriving a transformation matrix using the device matrix and frame coordinates of a plurality of reference key points from the image data set; and
projecting the at least one key point of the target area as the overlay on the visual feedback frame using the transformation matrix.
4. The method as in claim 1, wherein the iterative error correction mechanism minimizes difference between the at least one projected key point and the at least one located key point on the visual feedback frame by estimating parameters of an error function, wherein the error function is a function of position of the imaging device and position of the at least one projected key point.
5. A visual feedback system for visual feedback based calibration of a medical imaging system, wherein the visual feedback system comprises a calibration module configured to:
capture an image of a target area of the medical imaging system;
locate at least one key point present in the target area on a visual feedback frame of the captured image by determining frame coordinates for the at least one key point based on an image data set;
project the at least one key point of the target area as an overlay on the visual feedback frame using a mapping mechanism and the image data set, wherein the mapping mechanism converts real world coordinates of the at least on key point of the target area to frame coordinates of the visual feedback frame; and
perform calibration of the medical imaging system by applying an iterative error correction mechanism to minimize difference between the at least one projected key point and the at least one located key point on the visual feedback frame below a predefined threshold.
6. The visual feedback system as claimed in claim 5, wherein the calibration module is configured to generate the image data set by:
capturing a plurality of images of the target area by placing a pre-defined target pattern on the target area, wherein position of the target area and distance between the target area and the imaging device is varied for each captured image;
identifying a plurality of reference key points on the target to determine corresponding plurality of frame coordinates for the plurality of reference key points of the target area, wherein the frame coordinates for the plurality of reference points are derived from real world coordinates of the plurality of reference points that are received from the mechanical control module of the medical imaging system; and
storing the captured plurality of images along with meta data and frame co-ordinates of the plurality of reference key points of the target area.
7. The visual feedback system as claimed in claim 5, wherein the calibration module is configured to project the at least one key point of the target area as the overlay on the visual feedback frame using the mapping mechanism by :
computing a device matrix corresponding to a plurality of intrinsic parameters of the imaging device; and
deriving a transformation matrix using the device matrix and frame coordinates of a plurality of reference key points from the image data set; and
projecting the at least one key point of the target area as the overlay on the visual feedback frame using the transformation matrix.
8. The visual feedback system as claimed in claim 5, wherein the calibration module is configured minimize difference between the at least one projected key point and the at least one located key point on the visual feedback frame using the iterative error mechanism by estimating parameters of an error function, wherein the error function is a function of position of the imaging device and position of the at least one projected key point.

Dated this 17th of August 2016 Signature:
Name of the signatory: Dr. Kalyan Chakravarthy