Obstacle processing method and device of medical imaging system, electronic equipment, storage medium and program product

Abstract

The present disclosure relates to an obstacle processing method and device of a medical imaging system, an electronic device, a storage medium and a program product. The method comprises: acquiring, by a visible light camera, a camera image corresponding to a target working space of a target subsystem of the medical imaging system, wherein the target working space is a target movement path or an imaging beam range; detecting, based on the camera image, an obstacle in the target working space to obtain an obstacle detection result of the target working space; and in response to the obstacle detection result being that an obstacle is detected, performing obstacle processing on the target working space.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to an obstacle handling method for a medical imaging system, an obstacle handling device for a medical imaging system, an electronic device, a computer-readable storage medium, and a computer program product. Background Technology

[0002] During the positioning process of medical imaging systems, accidental collisions with obstacles or patients frequently occur due to the automatic movement of subsystems. For example, in an X-ray imaging system, when the X-ray tube is tracking the movement of the chest X-ray frame, the tube may hit the table or the patient; when the chest X-ray frame is tracking the X-ray tube in the opposite direction, the frame housing may hit the patient. These collisions can not only damage the equipment but also injure the patient, disrupting the smooth progress of the medical process.

[0003] Furthermore, obstructions within the imaging beam range can cause image artifacts during medical image acquisition by medical imaging systems. For example, in X-ray imaging systems, foreign objects within the X-ray fan-shaped beam range during exposure can lead to image artifacts. This not only reduces image quality and affects diagnostic accuracy but may also necessitate repeated exposures, increasing the radiation exposure risk for patients and healthcare workers. Summary of the Invention

[0004] This disclosure provides a technical solution for obstacle handling in a medical imaging system.

[0005] According to one aspect of this disclosure, a method for obstacle handling in a medical imaging system is provided, comprising:

[0006] The visible light camera acquires camera images corresponding to the target workspace of the target subsystem of the medical imaging system, wherein the target workspace is the target movement path or the imaging beam range;

[0007] Based on the camera images, obstacles in the target workspace are detected, and the obstacle detection results of the target workspace are obtained;

[0008] In response to the obstacle detection result indicating that an obstacle has been detected, obstacle processing is performed on the target workspace.

[0009] In one possible implementation, acquiring camera images corresponding to the target workspace of the target subsystem of the medical imaging system via a visible light camera includes:

[0010] A panoramic camera image corresponding to the medical imaging system is acquired by a visible light camera, wherein the panoramic camera image covers the target workspace of the target subsystem of the medical imaging system.

[0011] In one possible implementation, the camera image includes:

[0012] RGB color information and depth information;

[0013] or,

[0014] RGB color information.

[0015] In one possible implementation, the method further includes:

[0016] In response to the presence of an obstruction in the camera image, the visible light camera is moved and the camera image is re-acquired through the visible light camera.

[0017] In one possible implementation, detecting obstacles in the target workspace based on the camera image to obtain obstacle detection results for the target workspace includes:

[0018] The camera images are input into a pre-trained obstacle detection model, which then detects obstacles in the target workspace.

[0019] Based on the detection results of the obstacle detection model, the obstacle detection results of the target workspace are determined.

[0020] In one possible implementation, determining the obstacle detection results of the target workspace based on the detection results of the obstacle detection model includes:

[0021] The location of a preset type of object in the target workspace is identified by a pre-trained location recognition model, and the location recognition result of the preset type of object is obtained.

[0022] Based on the detection results of the obstacle detection model and the position recognition results of the preset type of object, the obstacle detection results of the target workspace are determined.

[0023] In one possible implementation, the location recognition model includes a tabletop location recognition model and / or a personnel location recognition model, and the preset type includes tabletop and / or personnel.

[0024] In one possible implementation, the obstacle handling of the target workspace includes:

[0025] Based on the coordinates of the obstacle, a bounding box surrounding the obstacle is displayed in the video stream of the visible light camera.

[0026] In one possible implementation, the obstacle handling of the target workspace includes:

[0027] Output obstacle warning messages.

[0028] In one possible implementation, when the target workspace is the target movement path, the obstacle handling of the target workspace includes:

[0029] In response to the distance between the target subsystem and the obstacle being less than or equal to a preset distance, the target subsystem is controlled to pause its movement; and in response to the obstacle being removed, the target subsystem is controlled to continue moving along the target movement path.

[0030] or,

[0031] Generate an alternative movement path to the target movement path, and control the target subsystem to move along the alternative movement path, wherein there are no obstacles on the alternative movement path;

[0032] or,

[0033] In response to the obstacle being a movable subsystem of the medical imaging system and the obstacle being in a state where movement is permitted, the obstacle is controlled to move to avoid the target movement path.

[0034] In one possible implementation, when the target workspace is within the imaging beam range, the obstacle handling of the target workspace includes:

[0035] Control the medical imaging system to pause medical image acquisition;

[0036] In response to the removal of the obstacle, the medical imaging system is allowed to continue acquiring medical images.

[0037] In one possible implementation, the medical imaging system is an X-ray imaging system;

[0038] The target subsystem includes at least one of the following: an X-ray emission subsystem, an X-ray detection subsystem, and a patient support subsystem.

[0039] In one possible implementation, the obstacle includes at least one of the following types: other subsystems of the medical imaging system, patients, technicians or medical staff, and other objects in the space where the medical imaging system is located.

[0040] According to one aspect of this disclosure, an obstacle handling device for a medical imaging system is provided, comprising:

[0041] The acquisition module is used to acquire camera images corresponding to the target workspace of the target subsystem of the medical imaging system through a visible light camera, wherein the target workspace is the target movement path or the imaging beam range;

[0042] The detection module is used to detect obstacles in the target workspace based on the camera image, and obtain the obstacle detection result of the target workspace;

[0043] The processing module is used to perform obstacle processing on the target workspace in response to the obstacle detection result indicating that an obstacle has been detected.

[0044] In one possible implementation, the acquisition module is used for:

[0045] A panoramic camera image corresponding to the medical imaging system is acquired by a visible light camera, wherein the panoramic camera image covers the target workspace of the target subsystem of the medical imaging system.

[0046] In one possible implementation, the camera image includes:

[0047] RGB color information and depth information;

[0048] or,

[0049] RGB color information.

[0050] In one possible implementation, the device further includes:

[0051] A motion module is used to control the visible light camera to move in response to the presence of an obstruction in the camera image, and to re-acquire the camera image through the visible light camera.

[0052] In one possible implementation, the detection module is used to:

[0053] The camera images are input into a pre-trained obstacle detection model, which then detects obstacles in the target workspace.

[0054] Based on the detection results of the obstacle detection model, the obstacle detection results of the target workspace are determined.

[0055] In one possible implementation, the detection module is used to:

[0056] The location of a preset type of object in the target workspace is identified by a pre-trained location recognition model, and the location recognition result of the preset type of object is obtained.

[0057] Based on the detection results of the obstacle detection model and the position recognition results of the preset type of object, the obstacle detection results of the target workspace are determined.

[0058] In one possible implementation, the location recognition model includes a tabletop location recognition model and / or a personnel location recognition model, and the preset type includes tabletop and / or personnel.

[0059] In one possible implementation, the processing module is used to:

[0060] Based on the coordinates of the obstacle, a bounding box surrounding the obstacle is displayed in the video stream of the visible light camera.

[0061] In one possible implementation, the processing module is used to:

[0062] Output obstacle warning messages.

[0063] In one possible implementation, when the target workspace is the target movement path, the processing module is configured to:

[0064] In response to the distance between the target subsystem and the obstacle being less than or equal to a preset distance, the target subsystem is controlled to pause its movement; and in response to the obstacle being removed, the target subsystem is controlled to continue moving along the target movement path.

[0065] or,

[0066] Generate an alternative movement path to the target movement path, and control the target subsystem to move along the alternative movement path, wherein there are no obstacles on the alternative movement path;

[0067] or,

[0068] In response to the obstacle being a movable subsystem of the medical imaging system and the obstacle being in a state where movement is permitted, the obstacle is controlled to move to avoid the target movement path.

[0069] In one possible implementation, when the target workspace is within the imaging beam range, the processing module is configured to:

[0070] Control the medical imaging system to pause medical image acquisition;

[0071] In response to the removal of the obstacle, the medical imaging system is allowed to continue acquiring medical images.

[0072] In one possible implementation, the medical imaging system is an X-ray imaging system;

[0073] The target subsystem includes at least one of the following: an X-ray emission subsystem, an X-ray detection subsystem, and a patient support subsystem.

[0074] In one possible implementation, the obstacle includes at least one of the following types: other subsystems of the medical imaging system, patients, technicians or medical staff, and other objects in the space where the medical imaging system is located.

[0075] According to one aspect of this disclosure, an electronic device is provided, comprising: one or more processors; a memory for storing executable instructions; wherein the one or more processors are configured to invoke the executable instructions stored in the memory to perform the method described above.

[0076] According to one aspect of this disclosure, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the above-described method.

[0077] According to one aspect of this disclosure, a computer program product is provided, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in an electronic device, a processor in the electronic device performs the above-described method.

[0078] In this embodiment, a visible light camera acquires camera images corresponding to the target workspace of a target subsystem of a medical imaging system. The target workspace is the target movement path or imaging beam range. Based on the camera images, obstacles in the target workspace are detected, resulting in an obstacle detection result. In response to the obstacle detection result indicating an obstacle has been detected, obstacle processing is performed on the target workspace. Thus, based on the camera images acquired by the visible light camera, obstacle detection and processing are performed on the movement path or imaging beam range of the subsystem of the medical imaging system. This reduces the need for sensors for obstacle detection and lowers the cost of obstacle processing in the medical imaging system. By detecting obstacles on the movement path of the subsystem of the medical imaging system and performing collision avoidance processing, the probability of collisions between the subsystem and patients or other obstacles can be reduced, thereby reducing damage to the medical imaging system caused by collisions and lowering the probability of harm to patients and other personnel. By detecting and processing obstacles within the imaging beam, artifacts in medical images can be reduced, improving image quality and accuracy of medical image-based diagnoses. This also reduces repeated exposures, thereby lowering the radiation exposure risk for patients and healthcare workers.

[0079] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure.

[0080] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0081] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the specification, serve to illustrate the technical solutions of this disclosure.

[0082] Figure 1 A flowchart illustrating an obstacle handling method for a medical imaging system provided in an embodiment of this disclosure is shown.

[0083] Figure 2 A schematic diagram of an X-ray imaging system is shown.

[0084] Figure 3 Another schematic diagram of an X-ray imaging system is shown.

[0085] Figure 4 A schematic diagram of the patient support subsystem is shown.

[0086] Figure 5 A block diagram of an obstacle handling device for a medical imaging system provided in an embodiment of this disclosure is shown.

[0087] Figure 6 A block diagram of an electronic device 1900 provided in an embodiment of this disclosure is shown. Detailed Implementation

[0088] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0089] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0090] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0091] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0092] This disclosure provides an obstacle handling method for a medical imaging system. It involves acquiring camera images of a target workspace corresponding to a target subsystem of the medical imaging system using a visible light camera. The target workspace is either a target movement path or an imaging beam range. Based on the camera images, obstacles in the target workspace are detected, resulting in an obstacle detection result. In response to the obstacle detection result indicating that an obstacle has been detected, obstacle handling is performed on the target workspace. This method, based on camera images acquired by a visible light camera, performs obstacle detection and handling on the movement path or imaging beam range of a subsystem of the medical imaging system, thereby reducing the need for sensors for obstacle detection and lowering the cost of obstacle handling in the medical imaging system. By detecting obstacles on the movement path of a subsystem of the medical imaging system and performing collision avoidance processing, the probability of collisions between the subsystem and patients or other obstacles can be reduced, thereby reducing damage to the medical imaging system caused by collisions and lowering the probability of injury to patients and other personnel. By detecting and processing obstacles within the imaging beam, artifacts in medical images can be reduced, improving image quality and accuracy of medical image-based diagnoses. This also reduces repeated exposures, thereby lowering the radiation exposure risk for patients and healthcare workers.

[0093] The obstacle handling method of the medical imaging system provided in this disclosure will be described in detail below with reference to the accompanying drawings.

[0094] Figure 1 A flowchart illustrating an obstacle handling method for a medical imaging system provided in this disclosure is shown. In one possible implementation, the entity executing the obstacle handling method of the medical imaging system can be an obstacle handling device of the medical imaging system. For example, the obstacle handling method of the medical imaging system can be executed by a terminal device, a server, or other electronic devices. The terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a personal digital assistant (PDA), a handheld device, or a computing device, etc. In some possible implementations, the obstacle handling method of the medical imaging system can be implemented by a processor calling computer-readable instructions stored in memory. Figure 1As shown, the obstacle handling method of the medical imaging system includes steps S11 to S13.

[0095] In step S11, a camera image corresponding to the target workspace of the target subsystem of the medical imaging system is acquired by a visible light camera, wherein the target workspace is the target movement path or the imaging beam range.

[0096] In step S12, obstacles in the target workspace are detected based on the camera image, and the obstacle detection result of the target workspace is obtained.

[0097] In step S13, in response to the obstacle detection result indicating that an obstacle has been detected, obstacle processing is performed on the target workspace.

[0098] A medical imaging system refers to a collection of devices used to acquire, process, store, transmit, and display images of the internal structures of the human body. Medical imaging systems play a crucial role in medical diagnosis, treatment planning, disease monitoring, and research. Medical imaging technology helps doctors observe detailed conditions inside the human body without the need for invasive surgery.

[0099] Medical imaging systems can include many types, such as X-ray imaging systems, CT (Computed Tomography) scanning systems, MRI (Magnetic Resonance Imaging) systems, ultrasound imaging systems, nuclear medicine imaging systems, and so on.

[0100] In this embodiment of the disclosure, the target subsystem of the medical imaging system can be an automatically movable subsystem within the medical imaging system, or a subsystem within the medical imaging system used to emit an imaging beam. The imaging beam can refer to various types of energy beams used in the medical imaging system to generate images. For example, the imaging beam can include X-ray beams used in X-ray imaging and CT scans, ultrasound beams used in ultrasound imaging, radio frequency pulses used in magnetic resonance imaging, and so on. For example, in a CT system, the imaging beam range can refer to the area covered by the helical or conical beam emitted when the X-ray source rotates; in an MRI system, the imaging beam range can refer to the area covered by the radio frequency signal; in an ultrasound imaging system, the imaging beam range can refer to the area covered by the ultrasound beam; and so on.

[0101] In one possible implementation, the medical imaging system is an X-ray imaging system; the target subsystem includes at least one of the following: an X-ray emission subsystem, an X-ray detection subsystem, and a patient support subsystem.

[0102] Figure 2 A schematic diagram of an X-ray imaging system is shown. Figure 2 In this system, the X-ray imaging system adopts a dual-column structure. Figure 2 The diagram illustrates an X-ray imaging system comprising an X-ray emission subsystem 21, an X-ray detection subsystem 22, and a patient support subsystem 23. The X-ray emission subsystem 21 may include an X-ray emitter and a column for mounting the emitter; the X-ray detection subsystem 22 may include an X-ray detector and a chest X-ray holder for mounting the detector; and the patient support subsystem 23 may include an examination table. Movements of the X-ray emission subsystem include: the column enabling the X-ray emitter to move laterally (along the length of the examination table); the X-ray emitter being able to move vertically or longitudinally relative to the column; and the X-ray emitter being able to rotate relative to the column.

[0103] Figure 3 Another schematic diagram of an X-ray imaging system is shown. Figure 3 The diagram illustrates an X-ray imaging system comprising an X-ray emission subsystem 31, an X-ray detection subsystem 32, and a patient support subsystem 33. The X-ray emission subsystem 31 employs a suspension structure, which includes guide rails, a retractable cylinder, an X-ray tube assembly, and a X-ray tube control device. The guide rails are mounted on the ceiling and consist of a set of vertically mounted rails. The retractable cylinder is mounted on the suspension structure. The X-ray tube assembly is mounted on the retractable cylinder and contains an X-ray source and a collimator. The X-ray source emits an X-ray beam, and the collimator is typically mounted below the X-ray source. The collimator is used to confine and shape the X-ray beam to ensure that X-rays irradiate only a specific area, while minimizing unwanted radiation to surrounding tissues and organs. The X-ray tube control device is mounted on the X-ray tube assembly and includes a user interface such as a display screen and control buttons for pre-image preparation, such as patient selection, protocol selection, and patient positioning. The movement of the X-ray emission subsystem includes: a vertically mounted guide rail that can move the X-ray tube assembly in the horizontal and vertical directions; a telescopic cylinder that can move the X-ray tube assembly in the vertical direction; the X-ray tube assembly that can rotate around the vertical direction; and the X-ray tube assembly that can rotate around a direction perpendicular to the screen plane of the X-ray tube control device.

[0104] The X-ray emission subsystem is the core component of an X-ray imaging system, responsible for generating an X-ray beam. It typically includes a vacuum tube containing a cathode (which emits electrons) and an anode (a target material, usually tungsten). Electrons are emitted from the cathode to the anode under high voltage, producing X-rays. These X-rays then pass through the patient's body, forming an image.

[0105] The X-ray detection subsystem is used to receive X-rays passing through a patient's body and convert them into digital signals so that a computer can process them and generate images. In a digital X-ray imaging system, the X-ray detection subsystem may include a flat panel detector (FPD), which can directly convert X-rays into digital images without the need for traditional film.

[0106] The movement of the X-ray detection subsystem can include: the chest frame can move the X-ray detector laterally (the length of the examination table), the X-ray detector can move vertically or longitudinally (the longitudinal direction of the examination table) relative to the chest frame, and the X-ray detector can rotate relative to the chest frame.

[0107] The patient support subsystem refers to the subsystem used by patients to lie down during X-ray examinations. The patient support subsystem can automatically move and adjust its position to ensure that the patient's body parts are correctly aligned with the X-ray beam and X-ray detector. This mobility is crucial for X-ray imaging at different angles and locations.

[0108] Figure 4 A schematic diagram of the patient support subsystem is shown. Figure 4 As shown, the patient support subsystem may include a foot pedal 41. The user can control the vertical movement of the examination table surface by operating the foot pedal of the patient support subsystem. When the user presses the foot pedal, it triggers the lifting mechanism of the examination table, allowing the table surface to rise or fall to adjust the patient's position to a suitable height for X-ray examination. When the user releases the foot pedal, a foot pedal release signal is generated, indicating that the user has completed the foot pedal operation. The foot pedal release signal can be used to stop the movement of the table surface or to confirm that the table surface has reached the desired position. In some possible implementations, releasing the foot pedal can also trigger other functions, such as locking the table surface position to ensure the patient remains stable during the X-ray examination.

[0109] In one possible implementation, where the target subsystem is an automatically movable subsystem within a medical imaging system, the target workspace of the target subsystem can be its target movement path. In this implementation, the target subsystem can be a component within the medical imaging system with automatic movement capabilities. The target subsystem is capable of moving along a predetermined path (i.e., the target movement path) to perform specific imaging tasks or adjust the patient's position. The target workspace can refer to the spatial area involved by the target subsystem during movement. For example, during a chest X-ray examination, the X-ray emitting subsystem can move vertically downwards to a position level with the patient's chest to image the chest from above. The target movement path of the X-ray detection subsystem can be opposite to that of the X-ray emitting subsystem, or it can rotate around the patient to capture images from different angles. The patient support subsystem can move vertically, horizontally, or tilt to adjust the patient's position, aligning the patient with the X-ray emitting and X-ray detection subsystems.

[0110] In another possible implementation, where the target subsystem is a subsystem in a medical imaging system used to emit an imaging beam, the target workspace of the target subsystem can be the spatial area covered by the imaging beam emitted by the target subsystem, i.e., the imaging beam range.

[0111] In one possible implementation, when the medical imaging system is an X-ray imaging system, the imaging beam range can also be referred to as the X-ray fan-shaped beam range, etc., without limitation. In X-ray imaging, the imaging beam range can be determined based on the collimation region. The collimation region can refer to the irradiation area of ​​the X-ray beam precisely defined using a collimator. Before X-ray imaging, the collimation region can be set by the user (e.g., a technician or medical professional). The user can adjust the position and angle of the collimator according to the specific needs of the examination to define the path and range of the X-ray beam.

[0112] In this embodiment of the disclosure, a camera image corresponding to the target workspace of the target subsystem of a medical imaging system can be acquired using at least one visible light camera. The visible light camera can refer to a device that captures images using light within the visible spectrum. The visible light camera can be used to record and analyze light that is perceptible to the human eye, i.e., light with wavelengths between approximately 400 nanometers (violet light) and 700 nanometers (red light). The camera image can refer to the image of the target workspace of the target subsystem captured by the visible light camera.

[0113] The visible light camera can be mounted in a fixed position within the scanning room, such as on the wall of the scanning room, or mounted on the medical imaging system, such as on a suspension structure, specifically on the side of the collimator, or fixed in any other way. In some embodiments, the camera image is not limited to a single optical image, but may also include a dynamic real-time video stream, i.e., a series of real-time optical images.

[0114] In one possible implementation, camera images of the target workspace of the target subsystem of the medical imaging system can be acquired using only a single visible light camera. This approach reduces the cost of obstacle handling in the medical imaging system.

[0115] In another possible implementation, camera images corresponding to the target workspace of the target subsystem of the medical imaging system can be acquired using at least two visible light cameras. In this implementation, the at least two visible light cameras can form a camera group or camera platform.

[0116] In one possible implementation, acquiring camera images corresponding to the target workspace of the target subsystem of the medical imaging system via a visible light camera includes: acquiring panoramic camera images corresponding to the medical imaging system via a visible light camera, wherein the panoramic camera images cover the target workspace of the target subsystem of the medical imaging system.

[0117] In this implementation, the panoramic camera images corresponding to the medical imaging system can cover the entire medical imaging system, including the target workspace of the target subsystem, i.e., the space in which the target subsystem is located throughout the entire operation. The panoramic camera images can help monitor and record the location, status, and surrounding environment of the target subsystem, ensuring the safety and accuracy of the target subsystem during operation.

[0118] In this implementation, panoramic camera images acquired by a visible light camera provide the medical imaging system with comprehensive visual feedback, thereby enabling more effective control and management of the target subsystem's operation within its target workspace.

[0119] In one possible implementation, the camera image contains RGB color information and depth information.

[0120] In this implementation, the camera image not only records the color information of the scene, but also includes the depth or distance information of each pixel relative to the camera. As an example of this implementation, the visible light camera can be an RGB-D camera, where "RGB" represents the three color channels of red, green, and blue, and "D" represents the depth channel.

[0121] RGB color information refers to the color data of each pixel in a camera image, represented by different intensities of the red, green, and blue color channels. RGB color information enables visible light cameras to capture color details in a scene, thus generating a color image. Depth information records the physical distance between each pixel in the scene and the visible light camera. In RGB-D cameras, depth information can be obtained through various techniques, such as structured light, time-of-flight (ToF), or stereo vision. A depth map can be represented as a two-dimensional matrix, where each pixel value corresponds to the actual distance, rather than brightness or color information. Depth information allows the camera to perceive the three-dimensional structure of the scene in which the medical imaging system is located, providing an additional dimension for obstacle detection and helping to improve the accuracy of obstacle detection.

[0122] In another possible implementation, the camera image includes RGB color information. In this implementation, the camera image may only contain RGB color information and not depth information.

[0123] In one possible implementation, the method further includes: in response to the presence of an obstruction in the camera image, controlling the visible light camera to move, and re-acquiring the camera image through the visible light camera.

[0124] In this implementation, if an obstruction is detected in the camera image—that is, if an object or person obstructs the target workspace of the target subsystem in the camera image, preventing the camera image from providing complete visual information of the target workspace—then the visible light camera can be moved to change its position or angle. Controlling the visible light camera movement aims to bypass or avoid the obstruction, thereby obtaining an unobstructed camera image.

[0125] After the visible light camera is moved, it can be used again to capture camera images. Since the position or angle of the visible light camera has changed, it is expected that camera images without obstructions can be obtained, thereby enabling more accurate monitoring and analysis of the target subsystem's operating status and surrounding environment.

[0126] This approach helps medical imaging systems continuously acquire complete and accurate visual information during operation, which is crucial for the safe operation and effective diagnosis of these systems. By dynamically adjusting the position of the visible light camera to avoid obstructions, it can adapt to complex and changing working environments, improving the quality and reliability of camera images.

[0127] In another possible implementation, the method further includes: issuing an occlusion warning message in response to the presence of an occlusion in the camera image; and re-acquiring the camera image using the visible light camera in response to the removal of the occlusion.

[0128] In this implementation, if an obstruction is detected in the camera image, an obstruction alert message can be automatically issued. This alert message can be a visual warning, an audible alarm, or other type of indication to notify the operator of the obstruction's presence. Upon receiving the alert, the operator can then take steps to remove the obstruction.

[0129] In another possible implementation, if there are occlusions in the camera image, obstacle detection can be performed on the target workspace based on the unoccluded image area in the camera image.

[0130] In this embodiment of the disclosure, after acquiring camera images corresponding to the target workspace of the target subsystem of the medical imaging system using a visible light camera, obstacles in the target workspace can be detected based on the camera images to obtain obstacle detection results for the target workspace. When the target workspace is a target movement path, an obstacle can be determined to be detected on the target movement path if the distance between any object (object or person) and the target movement path is less than or equal to a distance threshold. When the target workspace is within the imaging beam range, an obstacle, i.e., a foreign object, can be determined to be detected within the imaging beam range if any object is detected within the imaging beam range. The obstacle detection results for the target workspace may include whether an obstacle was detected or not. If the obstacle detection results for the target workspace include the detection of an obstacle, the results may further include at least some information such as the obstacle's location, type, and confidence level.

[0131] The location of obstacles can be represented by bounding boxes, two-dimensional coordinates, three-dimensional coordinates, etc., and is not limited here.

[0132] The type of obstacle can be represented by classification labels, integer codes, etc., without limitation. For example, the type of obstacle can be represented by predefined classification labels, such as "patient," "medical staff," "medical equipment," "furniture," etc. Alternatively, the type of obstacle can be represented by integer codes, such as 0 for "patient," 1 for "medical staff," 2 for "medical equipment," etc.

[0133] Confidence score is a metric that measures the certainty of a model's predictions. In this embodiment, confidence score can represent the model's degree of certainty regarding whether a detected object is an obstacle. Confidence score can be a value between 0 and 1; the higher the value, the more certain the model is that the object is an obstacle. In machine learning models, confidence score can be calculated in various ways. For example, in classification problems, the model can output a probability distribution, and the confidence score can be the probability of the category corresponding to the maximum value in this distribution.

[0134] In one possible implementation, the obstacle includes at least one of the following types: other subsystems of the medical imaging system, patients, technicians or medical staff, and other objects in the space where the medical imaging system is located.

[0135] As an example of this implementation, obstacles can include other subsystems in the medical imaging system besides the target subsystem. For instance, if the target subsystem is an X-ray emission subsystem, the patient support subsystem could also be an obstacle to the X-ray emission subsystem's path of movement toward the target.

[0136] As an example of this implementation, obstacles can include the patient. The patient is one of the most important considerations in a medical imaging system. For example, during X-ray imaging or other examinations, it is necessary to ensure the patient's safe position and prevent collisions with moving subsystems. Furthermore, potential patient movement can be considered to avoid accidents during imaging.

[0137] As an example of this implementation, obstacles could include technicians or medical personnel. Technicians or medical personnel are professionals who may be within the target's movement path or imaging beam during the operation of the medical imaging system. They may enter the target workspace while adjusting patient positions, operating equipment, or performing other medical procedures. Therefore, in this example, their safety is ensured by detecting the position of the technicians or medical personnel and stopping or adjusting the movement of the target subsystem as necessary.

[0138] As an example of this implementation, obstacles can include other objects in the space where the medical imaging system is located. For example, other objects in the space where the medical imaging system is located can include patient footstools, wheelchairs, IV stands, medical carts, and other medical instruments. These objects may inadvertently enter the target movement path or imaging beam range of the target subsystem, thereby creating safety hazards or affecting image quality.

[0139] In one possible implementation, the positions of individual subsystems (including the target subsystem) within a medical imaging system can be determined based on camera images. In this implementation, the position of the subsystem can be obtained by capturing its three-dimensional or two-dimensional coordinates in space using a visible light camera.

[0140] In another possible implementation, the position of the subsystem can be determined based on hardware feedback from the subsystem of the medical imaging system. In this implementation, the subsystem can be equipped with sensors or other positioning devices to directly provide the subsystem's position data. The position data provided by the sensors or other positioning devices can be the subsystem's absolute position (such as absolute coordinates) or relative position (such as its position in a robotic arm or C-arm).

[0141] In another possible implementation, the position of the subsystem can be determined by combining camera images and hardware feedback from the subsystem.

[0142] In one possible implementation, detecting obstacles in the target workspace based on the camera image and obtaining the obstacle detection result of the target workspace includes: inputting the camera image into a pre-trained obstacle detection model, detecting obstacles in the target workspace through the obstacle detection model; and determining the obstacle detection result of the target workspace based on the detection result of the obstacle detection model.

[0143] In this implementation, the obstacle detection model can be a machine learning model. For example, the obstacle detection model can be a YOLOv5 model, a Faster R-CNN model, an SSD model, etc., and there is no limitation here.

[0144] During the training phase of an obstacle detection model, a training image set containing a large number of training images can be used. These training images can be labeled with the bounding box coordinates of objects and the object type. The training images in the training image set can contain various variations to enable the obstacle detection model to generalize and detect obstacles of different sizes, angles, and environments. That is, the training image set can include images taken from different angles, under different lighting conditions, and in different backgrounds and scenes to cover various situations that may be encountered in real-world applications. By training the obstacle detection model using these labeled training images, the model can learn how to identify and locate specific objects in the images. During training, the obstacle detection model can continuously adjust its internal parameters to minimize the difference between the predicted bounding box and the ground truth bounding box, thereby improving the accuracy of obstacle detection.

[0145] The output of an obstacle detection model can include the location information of detected obstacles. For example, the location information of obstacles can be represented by bounding boxes. The bounding boxes can define the position and size of the obstacle in the image in coordinate form.

[0146] In one possible implementation, determining the obstacle detection result of the target workspace based on the detection result of the obstacle detection model includes: identifying the position of a preset type of object in the target workspace through a pre-trained position recognition model to obtain the position recognition result of the preset type of object; and determining the obstacle detection result of the target workspace based on the detection result of the obstacle detection model and the position recognition result of the preset type of object.

[0147] In this implementation, the location recognition model can be pre-trained and can be used to identify and locate specific types of objects (such as people, countertops, etc.) in the target workspace. That is, the location recognition model can identify objects of a preset type and provide their positional information in the image.

[0148] As an example of this implementation, a pre-trained location recognition model can identify the location of a preset type of object in the target workspace based on the camera image, and obtain the location recognition result of the preset type of object.

[0149] As an example of this implementation, in response to the presence of occlusions in the camera image, the position of a preset type of object in the target workspace can be identified by a pre-trained position recognition model to obtain the position recognition result of the preset type of object.

[0150] In this implementation, the output of the obstacle detection model can be combined with the output of the location recognition model (location information of predefined type objects) to determine the final detection result of obstacles in the target workspace. This combination can provide more comprehensive context awareness, helping to detect obstacles in the target workspace more accurately.

[0151] In one possible implementation, the location recognition model includes a tabletop location recognition model and / or a personnel location recognition model, and the preset type includes tabletop and / or personnel.

[0152] As an example of this implementation, the position recognition model includes a tabletop position recognition model, with the preset type being a tabletop. In this example, the tabletop position recognition model outputs the tabletop position recognition result, which may include the tabletop's height. By recognizing the tabletop's position, it is possible to help determine whether the tabletop is within the target workspace; that is, it is possible to help determine whether the tabletop is an obstacle within the target workspace.

[0153] In one example, a table position recognition model can use specific identification points (such as QR codes, reflective markers, or other identifiable features) to determine the position of a table (such as an X-ray examination table). Identification points are pre-placed on the table, and the model uses image recognition technology to detect these points and calculate their positions relative to a visible light camera, thus inferring the table's position. More than one identification point can be placed on the table; for example, identification points can be placed on both sides of the table. Using more than one identification point helps improve the accuracy of table position recognition. If an identification point is obstructed by personnel (e.g., a technician or medical staff standing in front of it), the table position can be recalculated after the personnel leave. If the table position cannot be determined based on the identification points, the table position can be reported as unknown.

[0154] As another example of this implementation, the location recognition model includes a personnel location recognition model, with preset types including personnel. By recognizing personnel locations, it can help determine whether there are personnel in the target workspace; that is, it can help determine whether personnel are obstacles within the target workspace. In one example, the personnel location recognition model can be used to identify whether a patient is lying on an examination bed.

[0155] In one possible implementation, obstacle detection can be performed solely using an obstacle detection model, without relying on a location recognition model. In this implementation, the types of obstacles detected by the obstacle detection model can include tabletops and people, as well as subsystems, footstools, wheelchairs, IV stands, medical carts, etc. Furthermore, in this implementation, the detection results of the obstacle detection model can be directly determined as the obstacle detection results for the target workspace.

[0156] In one possible implementation, if the target workspace is the target movement path and the obstacle detection result of the target workspace is that no obstacle is detected, the target subsystem can be controlled to move along the target movement path.

[0157] In one possible implementation, when the target workspace is within the imaging beam range and the obstacle detection result of the target workspace is that no obstacle is detected, it is permissible to control the medical imaging system to acquire medical images, such as X-ray exposure.

[0158] In one possible implementation, obstacle handling of the target workspace includes: displaying a bounding box surrounding the obstacle in the video stream of the visible light camera based on the coordinates of the obstacle.

[0159] In this implementation, after an obstacle is detected, its coordinates in the camera image can be obtained. These coordinates define the obstacle's position and boundaries in the camera image. Based on the obstacle's coordinates, bounding boxes can be drawn in the visible light camera's video stream to surround each detected obstacle. A bounding box is a visual marker used to highlight a specific object in an image or video frame. The bounding boxes are overlaid on the video stream, displaying the obstacle's position in real time.

[0160] By adopting this implementation method, operators can intuitively see the exact location of obstacles and make corresponding operational decisions accordingly. Displaying the bounding boxes of obstacles in the video stream provides real-time visual feedback, helping operators monitor the status of the target workspace and take timely measures to avoid potential collisions or artifacts.

[0161] As an example of this implementation, the confidence level that an object within a bounding box belongs to an obstacle can also be displayed in the video stream of the visible light camera. For example, in the visible light camera's video stream, the confidence level can be displayed as a decimal, percentage, or bar chart next to or inside each bounding box. This visualization helps operators quickly assess the reliability of obstacle detection results, allowing them to determine whether action is needed based on the confidence level. For example, if the confidence level is high, the operator might immediately take steps to remove the obstacle; if the confidence level is low, the operator might choose further observation or manual verification.

[0162] As an example of this implementation, the obstacle type to which the object in the bounding box belongs can also be displayed in the video stream of the visible light camera. For example, the obstacle type label can be directly displayed next to or inside each bounding box. For instance, if the detected obstacle is "patient," then the word "patient" can be displayed next to the bounding box.

[0163] As an example of this implementation, in a medical imaging system, a graphical user interface (GUI) can be used to display the video stream from a visible light camera, and the bounding box surrounding the obstacle can be displayed within the video stream. The GUI can be integrated into the main controller in the control room, or it can be directly embedded into the display screen of the X-ray tube control device of the X-ray emission subsystem, allowing operators to intuitively monitor and analyze the status of the target workspace and make timely operational decisions.

[0164] In one possible implementation, obstacle handling of the target workspace includes: outputting obstacle warning information.

[0165] Obstacle warning information can take many forms, including but not limited to visual cues (such as flashing icons or text messages on the screen), auditory cues (such as beeps or voice prompts), or other forms of notification, with the aim of immediately alerting operators to potential collision risks or imaging obstacles.

[0166] This implementation method improves the safety and reliability of medical imaging systems during operation. By providing timely obstacle warnings, technicians or medical staff can quickly take measures to prevent collisions between the medical imaging system and patients or other obstacles, reducing the risk of equipment damage, protecting patients from injury, and ensuring the continuity and quality of the imaging process. This proactive warning mechanism also helps reduce medical accidents caused by operational errors, improves medical staff's situational awareness of the surrounding environment, and thus optimizes the overall efficiency and diagnostic accuracy of the medical imaging system.

[0167] In one possible implementation, when the target workspace is the target movement path, the obstacle handling of the target workspace includes: controlling the target subsystem to pause movement in response to the distance between the target subsystem and the obstacle being less than or equal to a preset distance, and controlling the target subsystem to continue moving along the target movement path in response to the removal of the obstacle.

[0168] In this implementation, when the target subsystem (e.g., an X-ray emitting subsystem or an X-ray detection subsystem) moves along a predetermined path (i.e., the target movement path), the distance between the target subsystem and obstacles can be monitored in real time. If the distance between the target subsystem and the obstacle is less than or equal to a preset safe distance threshold (i.e., a preset distance), the movement of the target subsystem can be automatically paused to avoid potential collisions. Once the obstacle is removed, the movement of the target subsystem can be automatically resumed, allowing it to continue along the target movement path.

[0169] This implementation method improves the safety and reliability of medical imaging systems during operation. By automatically detecting obstacles and controlling the movement of the target subsystem, accidental collisions between the target subsystem and patients or other obstacles can be effectively prevented, reducing the risk of equipment damage, protecting patients from injury, and ensuring the safety of medical staff. Furthermore, this automatic control mechanism enhances the intelligence level of the medical imaging system, reduces the workload of operators, and makes the medical imaging process smoother and more efficient.

[0170] In one possible implementation, when the target workspace is the target movement path, the obstacle handling of the target workspace includes: generating an alternative movement path to the target movement path, and controlling the target subsystem to move along the alternative movement path, wherein there are no obstacles on the alternative movement path.

[0171] In this implementation, when the target subsystem of the medical imaging system encounters an obstacle on its target movement path, it can not only detect the obstacle but also intelligently generate a new alternative movement path that avoids it. Then, the movement of the target subsystem can be automatically adjusted so that it continues to perform its task along this new alternative path, ensuring that the necessary imaging operations are completed without colliding with the obstacle.

[0172] This implementation enhances the adaptability and flexibility of medical imaging systems in complex environments. By automatically avoiding obstacles and replanning paths, it ensures the continuity and efficiency of the imaging process, reducing imaging interruptions caused by obstacles. This not only improves image quality and reduces the need for repeated imaging, but also reduces the radiation exposure risk for patients and medical staff. Furthermore, it alleviates the decision-making burden on operators in complex situations, improving overall work efficiency and safety.

[0173] In one possible implementation, when the target workspace is the target movement path, the obstacle handling of the target workspace includes: in response to the obstacle being a movable subsystem of the medical imaging system and the obstacle being in a movement-permitted state, controlling the obstacle to move to avoid the target movement path.

[0174] In this implementation, if an obstacle on the target movement path is a movable subsystem of the medical imaging system (e.g., a movable X-ray detection subsystem or a patient support subsystem), and this movable subsystem is in a state where movement is permitted, these obstacles can be automatically moved to other locations to avoid the target movement path. This implementation not only detects obstacles but also actively adjusts their positions, thereby clearing obstacles from the movement path and ensuring that the target subsystem (such as the X-ray emission subsystem) can move smoothly without pausing or altering the predetermined workflow.

[0175] This implementation enhances the autonomy and flexibility of medical imaging systems in complex environments. By automatically moving obstacles to clear the path, imaging delays caused by obstacles are reduced, improving imaging efficiency while minimizing the need for manual equipment adjustments and reducing operational complexity. Furthermore, this automated obstacle handling mechanism reduces risks associated with human error, enhancing patient and healthcare worker safety and ensuring smoother and safer imaging operations.

[0176] In one possible implementation, when the target workspace is within the imaging beam range, the obstacle handling of the target workspace includes: controlling the medical imaging system to pause medical image acquisition; and allowing the medical imaging system to continue medical image acquisition in response to the removal of the obstacle.

[0177] In this implementation, when the target workspace of the medical imaging system is within the imaging beam range, the presence of obstacles within the imaging beam range can be monitored. If an obstacle is detected within the imaging beam range, the ongoing medical image acquisition process can be automatically paused to avoid imaging artifacts. Once the obstacle is removed, the process can be restarted, allowing the user to continue image acquisition. This approach ensures that image quality is not affected by obstacles and protects the patient from potential harm.

[0178] This implementation method ensures a clear and unobstructed imaging environment during medical image acquisition, thereby improving image quality and accuracy. By prompting or automatically clearing obstacles, it reduces duplicate exposures caused by obstructions, saving time and resources, and also lowering the radiation exposure risk for patients and healthcare personnel. Furthermore, this implementation method enhances the intelligence level of the medical imaging system, making operation safer and more efficient.

[0179] In one possible implementation, data can be exchanged between different components of the medical imaging system (such as the wall mount control platform and the position algorithm platform) via the Atlas data bus. The wall mount control platform receives data from the position algorithm platform and controls the movement and position of the wall mount for the X-ray emitter and detector based on this data. The position algorithm platform is a software platform that processes position-related algorithms such as obstacle detection, position tracking, and path planning. The position algorithm platform can use data collected from visible light cameras and other sensors to calculate obstacle position information and send commands to the wall mount control platform via CAN-BUS to control the position of the wall mount. The wall mount can refer to a support or support device used to carry the X-ray emitter and X-ray detector. In X-ray imaging systems, wall mounts can take different forms, primarily for supporting and moving the X-ray emitter and X-ray detector to facilitate imaging of the patient from different angles and positions. For example, the wall mount may include... Figure 2 The illustrated column and X-ray frame. Similarly, wall frames may include, for example,... Figure 3 The suspension structure and chest X-ray frame are shown.

[0180] It is understood that the various method embodiments mentioned above in this disclosure can be combined with each other to form combined embodiments without violating the principle and logic. Due to space limitations, this disclosure will not elaborate further. Those skilled in the art will understand that in the above methods of specific implementation, the specific execution order of each step should be determined by its function and possible internal logic.

[0181] In addition, this disclosure also provides an obstacle handling device, electronic device, computer-readable storage medium, and computer program product for a medical imaging system. All of the above can be used to implement any of the obstacle handling methods for a medical imaging system provided in this disclosure. The corresponding technical solutions and technical effects can be found in the relevant descriptions in the method section, and will not be repeated here.

[0182] Figure 5 This diagram illustrates a block diagram of an obstacle handling device for a medical imaging system provided in an embodiment of this disclosure. Figure 5 As shown, the obstacle handling device of the medical imaging system includes:

[0183] The acquisition module 51 is used to acquire camera images corresponding to the target workspace of the target subsystem of the medical imaging system through a visible light camera, wherein the target workspace is the target movement path or the imaging beam range.

[0184] The detection module 52 is used to detect obstacles in the target workspace based on the camera image and obtain the obstacle detection result of the target workspace;

[0185] The processing module 53 is used to perform obstacle processing on the target workspace in response to the obstacle detection result indicating that an obstacle has been detected.

[0186] In one possible implementation, the acquisition module 51 is used for:

[0187] A panoramic camera image corresponding to the medical imaging system is acquired by a visible light camera, wherein the panoramic camera image covers the target workspace of the target subsystem of the medical imaging system.

[0188] In one possible implementation, the camera image includes:

[0189] RGB color information and depth information;

[0190] or,

[0191] RGB color information.

[0192] In one possible implementation, the device further includes:

[0193] A motion module is used to control the visible light camera to move in response to the presence of an obstruction in the camera image, and to re-acquire the camera image through the visible light camera.

[0194] In one possible implementation, the detection module 52 is used for:

[0195] The camera images are input into a pre-trained obstacle detection model, which then detects obstacles in the target workspace.

[0196] Based on the detection results of the obstacle detection model, the obstacle detection results of the target workspace are determined.

[0197] In one possible implementation, the detection module 52 is used for:

[0198] The location of a preset type of object in the target workspace is identified by a pre-trained location recognition model, and the location recognition result of the preset type of object is obtained.

[0199] Based on the detection results of the obstacle detection model and the position recognition results of the preset type of object, the obstacle detection results of the target workspace are determined.

[0200] In one possible implementation, the location recognition model includes a tabletop location recognition model and / or a personnel location recognition model, and the preset type includes tabletop and / or personnel.

[0201] In one possible implementation, the processing module 53 is used to:

[0202] Based on the coordinates of the obstacle, a bounding box surrounding the obstacle is displayed in the video stream of the visible light camera.

[0203] In one possible implementation, the processing module 53 is used to:

[0204] Output obstacle warning messages.

[0205] In one possible implementation, when the target workspace is the target movement path, the processing module 53 is used to:

[0206] In response to the distance between the target subsystem and the obstacle being less than or equal to a preset distance, the target subsystem is controlled to pause its movement; and in response to the obstacle being removed, the target subsystem is controlled to continue moving along the target movement path.

[0207] or,

[0208] Generate an alternative movement path to the target movement path, and control the target subsystem to move along the alternative movement path, wherein there are no obstacles on the alternative movement path;

[0209] or,

[0210] In response to the obstacle being a movable subsystem of the medical imaging system and the obstacle being in a state where movement is permitted, the obstacle is controlled to move to avoid the target movement path.

[0211] In one possible implementation, when the target workspace is within the imaging beam range, the processing module 53 is configured to:

[0212] Control the medical imaging system to pause medical image acquisition;

[0213] In response to the removal of the obstacle, the medical imaging system is allowed to continue acquiring medical images.

[0214] In one possible implementation, the medical imaging system is an X-ray imaging system;

[0215] The target subsystem includes at least one of the following: an X-ray emission subsystem, an X-ray detection subsystem, and a patient support subsystem.

[0216] In one possible implementation, the obstacle includes at least one of the following types: other subsystems of the medical imaging system, patients, technicians or medical staff, and other objects in the space where the medical imaging system is located.

[0217] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments. The specific implementation and technical effects can be referred to the description of the above method embodiments. For the sake of brevity, they will not be repeated here.

[0218] This disclosure also provides a computer-readable storage medium storing computer program instructions thereon, which, when executed by a processor, implement the above-described method. The computer-readable storage medium may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium.

[0219] This disclosure also proposes a computer program including computer-readable code, wherein when the computer-readable code is run in an electronic device, a processor in the electronic device executes the above-described method.

[0220] This disclosure also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in an electronic device, the processor in the electronic device executes the above-described method.

[0221] This disclosure also provides an electronic device, including: one or more processors; a memory for storing executable instructions; wherein the one or more processors are configured to invoke the executable instructions stored in the memory to perform the above-described method.

[0222] Electronic devices can be provided as terminals, servers, or other forms of devices.

[0223] Figure 6 A block diagram of an electronic device 1900 provided according to an embodiment of this disclosure is shown. For example, the electronic device 1900 may be provided as a terminal or a server. (Refer to...) Figure 6 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by the processing component 1922. The application programs stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1922 is configured to execute instructions to perform the methods described above.

[0224] Electronic device 1900 may also include a power supply component 1926 configured to perform power management of electronic device 1900, a wired or wireless network interface 1950 configured to connect electronic device 1900 to a network, and an input / output interface 1958 (I / O interface). Electronic device 1900 can operate on an operating system stored in memory 1932, such as Microsoft Server operating system (Windows Server). TM Apple's graphical user interface-based operating system (MacOS X) TM ), a multi-user, multi-process computer operating system (Unix) TM Linux is a free and open-source Unix-like operating system. TM ), the open-source Unix-like operating system (FreeBSD) TM (or similar.)

[0225] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions that can be executed by a processing component 1922 of an electronic device 1900 to perform the above-described method.

[0226] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0227] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0228] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0229] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0230] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0231] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0232] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0233] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0234] The computer program product can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0235] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0236] If the technical solution of this disclosure involves personal information, the product applying the technical solution of this disclosure has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this disclosure involves sensitive personal information, the product applying the technical solution of this disclosure has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to indicate that the user has entered the scope of personal information collection and that personal information will be collected. If the user voluntarily enters the collection scope, it is deemed to have consented to the collection of their personal information; or on the personal information processing device, with clear signs / information informing the user of the personal information processing rules, authorization is obtained from the user through pop-up information or by asking the user to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0237] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method of obstacle processing of a medical imaging system, characterized in that, include: The visible light camera acquires camera images corresponding to the target workspace of the target subsystem of the medical imaging system, wherein the target workspace is the target movement path or the imaging beam range; Based on the camera images, obstacles in the target workspace are detected, and the obstacle detection results of the target workspace are obtained; In response to the obstacle detection result indicating that an obstacle has been detected, obstacle processing is performed on the target workspace.

2. The method of claim 1, wherein, The acquisition of camera images corresponding to the target workspace of the target subsystem of the medical imaging system via a visible light camera includes: A panoramic camera image corresponding to the medical imaging system is acquired by a visible light camera, wherein the panoramic camera image covers the target workspace of the target subsystem of the medical imaging system.

3. The method of claim 1, wherein, The camera image contains: RGB color information and depth information; or, RGB color information.

4. The method of claim 1, wherein, The method further includes: In response to the presence of an obstruction in the camera image, the visible light camera is moved and the camera image is re-acquired through the visible light camera.

5. The method according to any one of claims 1 to 4, characterized in that, The step of detecting obstacles in the target workspace based on the camera image and obtaining the obstacle detection result of the target workspace includes: The camera images are input into a pre-trained obstacle detection model, which then detects obstacles in the target workspace. Based on the detection results of the obstacle detection model, the obstacle detection results of the target workspace are determined.

6. The method of claim 5, wherein, The determination of obstacle detection results for the target workspace based on the detection results of the obstacle detection model includes: The location of a preset type of object in the target workspace is identified by a pre-trained location recognition model, and the location recognition result of the preset type of object is obtained. Based on the detection results of the obstacle detection model and the position recognition results of the preset type of object, the obstacle detection results of the target workspace are determined.

7. The method according to claim 6, characterized in that, The location recognition model includes a tabletop location recognition model and / or a personnel location recognition model, and the preset type includes tabletop and / or personnel.

8. The method according to any one of claims 1 to 4, characterized in that, The obstacle removal process for the target workspace includes: Based on the coordinates of the obstacle, a bounding box surrounding the obstacle is displayed in the video stream of the visible light camera.

9. The method according to any one of claims 1 to 4, characterized in that, The obstacle removal process for the target workspace includes: Output obstacle warning messages.

10. The method according to any one of claims 1 to 4, characterized in that, When the target workspace is the target movement path, the obstacle handling of the target workspace includes: In response to the distance between the target subsystem and the obstacle being less than or equal to a preset distance, the target subsystem is controlled to pause its movement; and in response to the obstacle being removed, the target subsystem is controlled to continue moving along the target movement path. or, Generate an alternative movement path to the target movement path, and control the target subsystem to move along the alternative movement path, wherein there are no obstacles on the alternative movement path; or, In response to the obstacle being a movable subsystem of the medical imaging system and the obstacle being in a state where movement is permitted, the obstacle is controlled to move to avoid the target movement path.

11. The method according to any one of claims 1 to 4, characterized in that, When the target workspace is within the range of the imaging beam, the obstacle removal process for the target workspace includes: Control the medical imaging system to pause medical image acquisition; In response to the removal of the obstacle, the medical imaging system is allowed to continue acquiring medical images.

12. The method according to any one of claims 1 to 4, characterized in that, The medical imaging system is an X-ray imaging system; The target subsystem includes at least one of the following: an X-ray emission subsystem, an X-ray detection subsystem, and a patient support subsystem.

13. The method according to any one of claims 1 to 4, characterized in that, The obstacle includes at least one of the following types: other subsystems of the medical imaging system, patients, technicians or medical staff, and other objects in the space where the medical imaging system is located.

14. An obstacle processing apparatus of a medical image system, characterized by, include: The acquisition module is used to acquire camera images corresponding to the target workspace of the target subsystem of the medical imaging system through a visible light camera, wherein the target workspace is the target movement path or the imaging beam range; The detection module is used to detect obstacles in the target workspace based on the camera image, and obtain the obstacle detection result of the target workspace; The processing module is used to perform obstacle processing on the target workspace in response to the obstacle detection result indicating that an obstacle has been detected.

15. An electronic device, comprising: include: One or more processors; Memory used to store executable instructions; The one or more processors are configured to invoke executable instructions stored in the memory to perform the method according to any one of claims 1 to 13.

16. A computer-readable storage medium having stored thereon computer program instructions, wherein, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1 to 13.

17. A computer program product comprising computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, characterized in that, When the computer-readable code is run in an electronic device, the processor in the electronic device performs the method according to any one of claims 1 to 13.

Images