Continuous patient observation during medical imaging examinations
The system addresses the challenge of continuous patient monitoring during imaging scans by using overhead and in-bore cameras to track and correct distortions, ensuring optimal patient observation and image quality throughout the scan.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- KONINKLIJKE PHILIPS NV
- Filing Date
- 2025-12-09
- Publication Date
- 2026-06-25
Smart Images
Figure EP2025085981_25062026_PF_FP_ABST
Abstract
Description
[0001] 2024PF00463 1
[0002] CONTINUOUS PATIENT OBSERVATION DURING MEDICAL IMAGING EXAMINATIONS
[0003] FIELD OF THE INVENTION
[0004] The invention relates to medical imaging and, in particular, to continuously monitoring a patient during a medical exam by an imaging scanner and / or system.
[0005] BACKGROUND OF THE INVENTION
[0006] Monitoring a patient during an imaging procedure is especially important for several reasons, such as patient movement and / or physical and mental well-being while undergoing the procedure. For example, it is desirable to detect breathing-related movements in order to prevent and correct for motion artifacts, ensure optimal image quality, and support respiratory triggered scans. Undesired patient motion is one of the main reasons for image quality issues and safety events, like finger pinching.
[0007] Moreover, for these monitoring applications it is particularly important to observe a predetermined region of interest of the patient. For instance, if breathing motions should be monitored, the chest of the patient has to be monitored, or, if a well-being of the patient should be monitored, the face of the patient has to be monitored. Since during certain medical scans, like CT or magnetic resonance (MR) for example, the patient may be moved through the imaging device, and this region of interest has to be tracked in the provided monitoring images.
[0008] During an imaging procedure, a medical professional (user) needs to watch the patient during the entire examination in order to quickly identify and react to any kind of abnormal patient conditions, such as anxiety, pain, moves, faint, etc. Typically, monitoring video images provided by cameras, such as wide field of view cameras, are used for such observations.
[0009] In order to achieve this, the healthcare institution usually installs a camera and a separate dedicated monitor on the desk. Such approach has several disadvantages. For example, a single camera can’t efficiently cover the entire range that the CT couch moves during the examination. Even if two or more surveillance cameras are mounted in a scanning room to capture both front and rear views of the scanner, only a partial view, at best, can be obtained during the scans. Most of the anatomy is likely to be occluded due to the shape of the patient, the limited diameter of the bore through the scanning system, and the presence of positioning or medical devices. 2024PF00463 2
[0010] The surveillance system cannot provide a continuous view of the relevant body parts of the patient throughout the whole examination, especially when the patient support with the patient travels through the scanner.
[0011] Hence, there is an ongoing need and desire to improve patient monitoring in imaging procedures. In particular, there is ongoing need and desire to address the difficulty and / or inability to observe the patient during the entire imaging examination while the couch is in motion and the patient on the couch moves to various locations, outside and inside the scanner bore.
[0012] SUMMARY OF THE INVENTION
[0013] The present invention addresses the above needs and desires. In particular, the present invention automatically identifies a region of interest (ROI) to monitor the patient and continuously keep the view of the ROI regardless of the couch position inside or outside the scanner bore.
[0014] According to one embodiment of the present invention, disclosed is a computer implemented method for processing images of a patient positioned on a patient support during an imaging scan. According to the method a scanner is provided for scanning the patient. The scanner has a bore through which the patient support is translated. An overhead optical camera is positioned for capturing images of the patient and located outside the scanner. An in-bore optical camera is positioned inside the bore for capturing images of the patient inside the bore. At least one processor is configured to define a region of interest on the patient, continuously track the region of interest during translation of the patient support by automatically switching views between the overhead optical camera and the in-bore optical camera, correct distortions within the images resulting from a wide field of view of the in-bore optical camera, and generate and output distortion-corrected images of the region of interest to a display.
[0015] According to another embodiment of the present invention, disclosed is a system for processing images of a patient during an imaging scan. The system comprises a patient support for positioning a patient during the imaging scan and a scanner for scanning the patient. The scanner has a bore through which the patient support is translated. The system further includes an overhead optical camera for capturing images of the patient, the overhead camera being located outside the scanner. The system also comprises an in-bore optical camera inside the bore for capturing images of the patient inside the bore. Also included in the system is at least one processor configured to define a region of interest on the patient, 2024PF00463 3 continuously track the region of interest during translation of the patient support by automatically switching views between the overhead optical camera and the in-bore optical camera, correct distortions within the images resulting from a wide field of view of the inbore optical camera, and generate and output distortion-corrected images of the region of interest to a display.
[0016] According to yet another embodiment of the present invention, disclosed is a non- transitory computer-readable medium comprising executable instructions which, when executed by at least one processor, cause the at least one processor to perform a method for processing images of a patient positioned on a patient support during an imaging scan. According to the method, a scanner is provided for scanning the patient, the scanner having a bore through which the patient support is translated. According to the method, an overhead optical camera is positioned for capturing images of the patient, the overhead camera being located outside the scanner. Further according to the method, at least one in-bore optical camera is positioned inside the bore for capturing images of the patient inside the bore. Also according to the method, at least one processor is configured to define a region of interest on the patient, continuously track the region of interest during translation of the patient support by automatically switching views between the overhead optical camera and the in-bore optical camera, correct distortions within the images resulting from a wide field of view of the at least one in-bore optical camera, and generate and output distortion-corrected images of the region of interest to a display.
[0017] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter.
[0018] BRIEF DESCRIPTION OF THE DRAWINGS
[0019] For a better understanding of the invention and to show more clearly how it may be carried into effect, reference is made, by way of example only, to the accompanying drawings, in which:
[0020] Figure 1 illustrates a block diagram of the system according to one embodiment of the present invention;
[0021] Figure 2A and Figure 2B illustrate monitoring the location of a region of interest based on the joints identification in accordance with one embodiment of the present invention; 2024PF00463 4
[0022] Figure 3 illustrates an original distorted image, an undistorted image and a distortion- corrected sequence of images with different parameters in accordance with one embodiment of the present invention;
[0023] Figure 4 schematically illustrates the system according to another embodiment of the present invention; and
[0024] Figure 5 illustrates a block diagram of the method according to one embodiment of the present invention.
[0025] DETAILED DESCRIPTION OF THE EMBODIMENTS
[0026] It should be understood that the detailed description and specific examples, while indicating exemplary embodiments of the system, storage medium and method, are intended for purposes of illustration only and are not intended to limit the scope of the invention. These and other features, aspects, and advantages of the present invention will become better understood from the following description, appended claims, and accompanying drawings. It should be understood that the Figures are merely schematic and are not drawn to scale. It should also be understood that the same reference numerals are used throughout the Figures to indicate the same or similar parts.
[0027] According to one embodiment of the invention, a patient is continuously observed on a display during the entire examination by following a predetermined region of interest on the patient, and automatically switching between various cameras to show an optimal view of the region of interest, thereby improving the user workflow by not requiring the system user to repeat the scan.
[0028] Figure 1 shows schematically a system 100 for capturing and processing optical images of a patient during a CT scan, as an example only.
[0029] The system 100 comprises a scanner 140 that is configured to acquire a medical image, i.e. a CT image in this example, of a patient 121 positioned on a patient support (couch) 120 during a scan. The patient support 120 is adopted to move the patient 121 through a bore 145 of the scanner during the imaging examination. The scanner 140 has a drive system 124 for moving the patient support through the bore 145.
[0030] As further shown in Figure 1, the system 100 comprises an overhead optical camera 190 located outside the scanner 140 and configured to acquire images of the patient positioned on the patient support 120. The system 100 further includes an in-bore optical camera 130 positioned inside the scanner bore and configured to capture images of the patient 121 while inside the bore 145 during the imaging examination. Also shown in Figure 2024PF00463 5
[0031] 1 is a processor 150. The operation of the system with a single camera - color or monochrome - and a single processor will be explained, but there may be multiple cameras as explained and shown further below. It is also understood that multiple processors may be used in the system.
[0032] The processor 150 is configured to define or locate a region of interest of the patient using a ROI selection unit 160. The ROI selection unit 160 is configured to focus the optical cameras - either overhead or in-bore - on the region of interest automatically by identifying joints on the patient. The joints identification is implemented by a software module using, for example, a predetermined medical database. Namely, the cameras can focus on the patient’s face based on the identified “head” joint as shown in Figure 2A. Alternatively, the cameras can focus on the patient’s intravenous (IV) site based on the identified “elbow” or “hand” joint, as shown in Figure 2B.
[0033] In another embodiment of the present invention, the system user provides commands via a user interface to the ROI selection unit 160 to define or locate the region of interest. Using panning or zooming function, the user selects the ROI on a display 180.
[0034] In yet another embodiment of the present invention, the region of interest is selected semi-automatically based on the selection of the surview range and / or scan range. The surview or clinical scan range (start / end of the area to be scanned) can be done either manually during the planning stage or automatically based on, for instance, camera view (for surview scan range) or 2D / 3D surview (for clinical scan range). In both scenarios, this range can serve as the area to auto-focus on for continuing patient observation. It is useful for a user to detect, for instance, patient not being still during the scanning.
[0035] The processor 150 tracks at least one region of interest of the patient during the displacement or translation of the patient support 120 in and out of the scanner bore. A tracking unit implements such tracking 162. The region of interest may be a body part to be monitored, such as the face, an area to be scanned, an area of IV injection, and / or the hands, as shown in Figure 2A and Figure 2B, for example. The location of the region of interest in an optical image can be defined manually, semi-manually or automatically by appropriate algorithms (for example, using key point detection algorithms), which locate the region of interest that includes a selected anatomical feature of interest.
[0036] In tracking the region of interest, the tracking unit 162 is configured to continuously acquire the couch position via the optical cameras. Whenever the couch moves, the camera image is automatically auto-zoomed to cover that area. The processor will automatically switch among the optical cameras to select an optimal view (described in detail below). 2024PF00463 6
[0037] Alternatively, the user can switch the camera manually. Optionally, one or more camera views are shown simultaneously on the display 180.
[0038] The selection of the optimal view to be displayed on the display 180 is based on one or more of the following principles:
[0039] 1) The distance and angle between the selected region of interest and each camera are computed. An image or sequence of images from the camera having the most advantageous properties, such as the lowest distance or greatest end-to-end pixel resolution, least oblique orientation to the face, is selected for the optimal view.
[0040] 2) The features within the located region of interest are analysed and scored. The data stream having the highest score is then selected as the optimal view. For example, the presence and visibility of the eyes and mouth in the displayed image can lead to a higher score. Such specific facial landmarks are detected by a face detection algorithm.
[0041] 3) The confidence score of the detection algorithm is used as criterion for the optimal view. The view having the highest confidence is then selected.
[0042] 4) Time filtering is applied in order to avoid switching between the different views too rapidly or too many times back and forth. For example, each video stream accumulates points over time for each displayed frame. The score for each frame is then computed as described above. The video stream with the highest integral score over a given sliding interval is selected at each time point as the optimal view.
[0043] 5) Fixed rules are applied depending on the patient orientation and the region to be scanned. For example, for a feet first examination with a targeted anatomy comprised between the lower extremities and the pelvis, the view from the overhead optical camera is selected for the optimal view. In contrast, for a head-first brain examination, the view from the in-bore optical camera is selected for the optimal view.
[0044] The in-bore camera 130 has a wide field of view to capture a full view of the patient support 120 or at least the part of the patient support 120 over which regions of interest of the patient will be positioned. The camera, for example, comprises a fisheye lens with a field of view greater than 150 degrees, for example 160 degrees or more. Thus, the patient support, as well as the patient on the patient support, can be imaged either by a single camera, as shown in Figure 1 or by two or more cameras, as shown in Figure 4 (described below).
[0045] It is known that the wide angle lens contribute to image distortion, such that the shape of objects appears differently at different regions of the field of view of the camera, as shown in Figure 3. As a result, the shape of objects or regions of interest will change when the 2024PF00463 7 position of those objects or regions of interest change in the field of view of the camera as a result of the movement of the patient support.
[0046] To address this issue, the processor 150 performs, among other things, image postprocessing to correct those distortions within the captured optical images, i.e., resulting from the width of the field of view of the camera. For the purposes of the post-processing, the inbore optical cameras are calibrated, such that geometric distortions are corrected by the postprocessing, whereby the position and orientation of each camera with respect to the scanner coordinate system is known.
[0047] The processor 150 then generates a distortion-corrected sequence of images of the region of interest. This is implemented by a post-processing unit 164 of Figure 1. Figure 3 illustrates an original distorted image, an undistorted image and a distortion-corrected sequence of images with different parameters in accordance with one embodiment of the present invention.
[0048] The distortion-corrected image sequence is provided as an output 170 to be displayed on a display 180. The display 180 may be part of the medical scanner or, alternatively, it may be a separate device, such as a mobile device of a technician. In yet another embodiment, the display 180 may be part of a remote operation center, to which the image data is transmitted by wired or wireless data transfer.
[0049] The output 170 comprises a continuous video stream. There may be a video stream of one or multiple regions of interest.
[0050] In a further embodiment, an additional camera located in the CT examination room can provide a video stream of the patient as he / she moves into the room towards the couch. The same steps and functions as described above, with this additional video stream as further input, will apply.
[0051] Figure 4 illustrates another embodiment of the present invention. According to this embodiment, 2 in-bore optical cameras 130a and 130b are located inside the bore of the scanner. This alternative embodiment with 2 in-bore cameras offers better continuous coverage and monitoring of the patient inside the bore during a scan. The views are switched from one camera to another based on the optimum view. All other elements in this Figure are functionally identical to those in Figure 1.
[0052] Figure 5 illustrates a block diagram of the method according to one embodiment of the present invention. In block 500, a scanner is provided for scanning the patient, wherein the scanner has a bore through which the patient support is translated. In block 502, an overhead optical camera is positioned for capturing images of the patient. The overhead 2024PF00463 8 camera is located outside the scanner. In block 504, an in-bore optical camera is positioned inside the bore for capturing images of the patient inside the bore during an examination. In block 506, at least one processor is configured to define a region of interest on the patient. In block 508, the at least one processor continuously tracks the region of interest during translation of the patient support by automatically switching views between the overhead optical camera and the in-bore optical camera. In block 510, the at least one processor corrects distortions within the images resulting from a wide field of view of the in-bore optical camera. In block 512, the at least one processor generates and outputs distortion- corrected images of the region of interest to a display.
[0053] The person skilled in the art would be readily capable of developing a device for carrying out any herein proposed method. The device comprises processing circuitry and a memory containing instructions that, when executed by the processing circuitry, configure the processing circuitry to perform any herein proposed method. Thus, each step of any proposed method may represent a different action performed by processing circuitry and may be performed by a respective module of the processing circuitry.
[0054] Embodiments may therefore make use of processing circuitry. The processing circuitry can be implemented in numerous ways, with software and / or hardware, to perform the various functions required. A processor is one example of processing circuitry which employs one or more microprocessors that may be programmed using software (e.g., microcode) to perform the required functions. Processing circuitry may however be implemented with or without employing a processor, and also may be implemented as a combination of dedicated hardware to perform some functions and a processor (e.g., one or more programmed microprocessors and associated circuitry) to perform other functions.
[0055] Examples of processing circuitry components that may be employed in various embodiments of the present disclosure include, but are not limited to, conventional microprocessors, application specific integrated circuits (ASICs), and field-programmable gate arrays (FPGAs).
[0056] The processing circuitry is associated with memory (i.e., one or more storage media) such as volatile and non-volatile computer memory such as RAM, PROM, EPROM, and EEPROM. The memory comprises instructions that, when executed by the processing circuitry, configure the processing circuitry to perform any herein proposed method. Thus, the memory may be encoded with one or more programs that, when executed on processing circuitry, perform the required functions. Various memories may be fixed within the 2024PF00463 9 processing circuitry or may be transportable, such that the one or more programs stored thereon can be loaded into the processing circuitry.
[0057] It will be understood that disclosed methods are preferably computer-implemented methods. As such, there is also proposed the concept of a computer program comprising code means for implementing any described method when said program is run on processing circuitry, such as a computer. Thus, different portions, lines or blocks of code of a computer program according to an embodiment may be executed by processing circuitry (e.g., a computer) to perform any herein described method.
[0058] There is also proposed a non-transitory storage medium that stores or carries a computer program or computer code that, when executed by processing circuitry, causes the processing circuitry to carry out any herein described method.
[0059] In some alternative implementations, the functions noted in the block diagram(s) or flow chart(s) may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
[0060] Variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure and the appended claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.
[0061] In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. If the term "adapted to" is used in the claims or description, it is noted the term "adapted to" is intended to be equivalent to the term "configured to". If the term "arrangement" is used in the claims or description, it is noted the term "arrangement" is intended to be equivalent to the term "system", and vice versa.
[0062] A single processor or other unit may fulfill the functions of several items recited in the claims. If a computer program or software is discussed above, it may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.
[0063] Any reference signs in the claims should not be construed as limiting the scope.
Claims
2024PF00463 10CLAIMS1. A computer implemented method for processing images of a patient positioned on a patient support during an imaging scan, comprising: providing a scanner for scanning the patient, wherein the scanner has a bore through which the patient support is translated; positioning an overhead optical camera for capturing images of the patient, wherein the overhead camera is located outside the scanner; positioning an in-bore optical camera inside the bore for capturing images of the patient inside the bore; and providing at least one processor configured to: define a region of interest on the patient; continuously track the region of interest during translation of the patient support by automatically switching views between the overhead optical camera and the inbore optical camera; correct distortions within the images resulting from a wide field of view of the in-bore optical camera; and generate and output distortion-corrected images of the region of interest to a display.
2. The method according to claim 1, wherein the region of interest is defined automatically based on joints identification on the patient.
3. The method according to claim 1, wherein the region of interest is defined manually by a user, wherein the user modifies, by panning and / or zooming, the region of interest within the images.
4. The method according to claim 3, wherein the at least one processor is configured to track the modified region of interest.
5. The method according to claim 1, further comprising an additional in-bore camera.
6. The method according to claim 5, wherein the at least one processor is configured to find an optimal view of the region of interest during the continuous tracking by automatically2024PF00463 11 switching views among the overhead optical camera, the in-bore optical camera, and the additional in-bore camera.
7. The method according to claim 1, wherein the at least one processor is configured to find an optimal view of the region of interest during the continuous tracking by automatically switching views between the overhead optical camera and the in-bore optical camera.
8. The method according to claim 6 or 7, wherein the at least one processor is configured to find the optimal view by determining a distance and an angle between the defined region of interest and each of the optical cameras, such that a view from the optical camera having the most advantageous distance and angle is selected.
9. The method according to claim 6 or 7, wherein the at least one processor is configured to find the optimal view by analyzing features within the region of interest and calculating a score based on the analyzed features, such that a view from the optical camera having the highest score is selected.
10. The method according to claim 6 or 7, wherein the views are switched between the overhead optical camera and the in-bore optical camera using a time filtering operation.
11. The method according to claim 6 or 7, wherein the views are switched between the overhead optical camera and the in-bore optical camera according to a predetermined rule.
12. A system for processing images of a patient during an imaging scan, comprising: a patient support for positioning a patient during the imaging scan; a scanner for scanning the patient, wherein the scanner has a bore through which the patient support is translated; an overhead optical camera for capturing images of the patient, wherein the overhead camera is located outside the scanner; an in-bore optical camera inside the bore for capturing images of the patient inside the bore; and at least one processor configured to: define a region of interest on the patient;2024PF00463 12 continuously track the region of interest during translation of the patient support by automatically switching views between the overhead optical camera and the inbore optical camera; correct distortions within the images resulting from a wide field of view of the in-bore optical camera; generate distortion-corrected images of the region of interest; and output the distortion-corrected images of the region of interest to a display.
13. A non-transitory computer-readable medium comprising executable instructions which, when executed by at least one processor, cause the at least one processor to perform a method for processing images of a patient positioned on a patient support during an imaging scan, the method comprising: providing a scanner for scanning the patient, wherein the scanner has a bore through which the patient support is translated; positioning an overhead optical camera for capturing images of the patient, wherein the overhead camera is located outside the scanner; positioning at least one in-bore optical camera inside the bore for capturing images of the patient inside the bore; and providing at least one processor configured to: define a region of interest on the patient; continuously track the region of interest during translation of the patient support by automatically switching views between the overhead optical camera and the inbore optical camera; correct distortions within the images resulting from a wide field of view of the at least one in-bore optical camera; generate distortion-corrected images of the region of interest; and output the distortion-corrected images of the region of interest to a display.