Determine the control parameters of the light source

Abstract

This document discloses a method for determining one or more control parameters (416) for controlling one or more light sources (142) to adjust the illumination conditions of a medical imaging system (100) during the acquisition of optical sensor data (414) using an optical sensor (144). The method includes activating a feedback loop in response to receiving an adjustment trigger. The feedback loop includes controlling the adjustment of illumination conditions using one or more light sources (142), receiving adjusted optical sensor data (414) from the optical sensor (144) for the adjusted illumination conditions, detecting a target element (122) within the adjusted optical sensor data (414) using a target detection module (412), and determining a confidence value for the detection of the target element (122). The feedback loop is repeated until the confidence value determined for the detection of the target element (122) reaches a predefined confidence threshold level.

Description

Technical Field

[0001] This invention relates to medical imaging, and more particularly to a method for determining one or more control parameters for controlling one or more light sources to adjust the illumination conditions of a medical imaging system during the acquisition of optical sensor data using an optical sensor. The optical sensor is configured to monitor the medical imaging system. Furthermore, this invention relates to a computer program including machine-executable instructions for performing the method, a computing device for performing the method, and a medical imaging system including the computing device. Background Technology

[0002] In the scanning environment of modern medical imaging systems, lighting can be fully adapted to individual preferences, such as those of the patient and / or operator. This adaptation can be achieved not only in terms of illuminance levels, but also by the availability and application of various color schemes (e.g., to improve the environmental experience). Such features have been shown to help reduce stress for both patients and operators, and to contribute to creating a friendly and comfortable scanning environment and atmosphere.

[0003] However, such adaptive lighting changes can pose challenges to the supervision of medical imaging systems, as modules used for such supervision are typically configured to perform supervision under specific lighting conditions. The accuracy and / or effectiveness of supervision may be reduced when the actual lighting conditions of the medical imaging system (e.g., for improved environmental experience) deviate from the lighting conditions for which the corresponding modules were originally configured. Summary of the Invention

[0004] This invention provides a method for determining one or more control parameters for controlling one or more light sources to adjust the illumination conditions of a medical imaging system during the acquisition of optical sensor data using an optical sensor; a computer program for determining one or more control parameters, the computer program including machine-executable instructions for controlling one or more control parameters to adjust the illumination conditions of the medical imaging system during the acquisition of optical sensor data using an optical sensor; and a computing device for determining one or more control parameters for controlling one or more light sources to adjust the illumination conditions of the medical imaging system during the acquisition of optical sensor data using an optical sensor. Furthermore, this invention provides a medical imaging system including a computing device for determining one or more control parameters for controlling one or more light sources to adjust the illumination conditions of the medical imaging system during the acquisition of optical sensor data using an optical sensor.

[0005] In one aspect, the present invention provides a method for determining one or more control parameters for controlling one or more light sources to adjust illumination conditions of a medical imaging system during the acquisition of optical sensor data using an optical sensor. The optical sensor is configured to monitor the medical imaging system. A computing device for performing the method includes a target detection module configured to detect target elements of one or more target structures within the optical sensor data in response to receiving optical sensor data from the optical sensor.

[0006] The method includes receiving data from the optical sensor.

[0007] The target element within the optical sensor data is detected by using the target detection module.

[0008] A feedback loop is activated in response to receiving an adjustment trigger. The feedback loop includes: controlling the adjustment of illumination conditions of the medical imaging system using one or more light sources; receiving adjusted optical sensor data from the optical sensor for the adjusted illumination conditions; detecting the target element within the adjusted optical sensor data using the target detection module; and determining a confidence value for the detection of the target element within the adjusted optical sensor data.

[0009] The feedback loop is repeated until the confidence value determined for the detection of the target element within the adjusted optical sensor data reaches a predefined confidence threshold level. One or more adjustment parameters that define the adjustment of the lighting conditions, causing the confidence value to reach the predefined confidence threshold level, are determined as the one or more control parameters.

[0010] The detection quality of target elements within the optical sensor data of a medical imaging system can depend on the illumination conditions of the medical imaging system. Target detection modules used to detect target elements are typically configured to detect them under specific illumination conditions. It is recommended to use a feedback loop to determine one or more adjustment parameters that define adjustments for a given illumination condition, such that the confidence value for the detection of the target element reaches and / or exceeds a predefined confidence threshold level. These one or more adjustment parameters are used as one or more control parameters to control one or more light sources to adjust the illumination conditions of the medical imaging system during the acquisition of optical sensor data using the optical sensor. Therefore, it can be ensured that optical sensor data is acquired under adjusted illumination conditions, thereby ensuring a sufficient confidence value for the detection of the target element.

[0011] Feedback loops and therefore adjustments to lighting conditions can be performed only when necessary (i.e., in response to receiving an adjustment trigger).

[0012] The example may have the beneficial effect of using feedback loops to determine adjustment parameters for a variety of types of given lighting conditions. Furthermore, there is no need to know a priori what the lighting conditions might look like to ensure a sufficient confidence value, nor which parameter must be adjusted to ensure a sufficient confidence value. For example, by using feedback loops, only the minimal adjustments needed to ensure a sufficient confidence value can be implemented.

[0013] The example allows for the retention of suitable detection performance, which can be extended to a wide range of lighting preferences, both in terms of light level and color, by using a feedback loop. This suitable detection performance could be, for example, achievable under normal lighting conditions in the working environment or under any other reference lighting environment that may have been used to configure the target detection module.

[0014] The example demonstrates how a light source can provide stable illumination. This illumination can be used stably to monitor medical imaging systems, particularly for the detection of target structures.

[0015] Supervision can include, for example, monitoring the preparation of a patient for an examination using a medical imaging system. This supervision can be automated or at least partially automated by combining optical sensors with a target detection module. Such preparation can be time-consuming. Automating preparation in this way avoids diverting the attention of trained and skilled operators from the patient. This allows operators to better focus on the patient. Furthermore, by taking over time-consuming tasks such as patient preparation, operator stress levels can be reduced or kept within limits. This is possible even under high-throughput conditions (e.g., due to hospital department productivity goals). Thus, limitations in the consistency of examination quality, compromised patient and / or staff experience, and increased risk of errors (including harm to the patient) can be effectively avoided.

[0016] By combining optical sensors with target detection modules, medical imaging systems can assist operators in patient examination settings, allowing the detection of desired and undesirable use and / or configurations of the medical imaging system. For example, unsafe system use and / or unsafe configurations can be detected. For instance, the patient's position (e.g., on a patient bed) and / or the position of components of the medical imaging system (e.g., cables and / or coils) can be determined, particularly relative to the patient's position.

[0017] To detect target elements, an object detection module, such as one incorporating a neural network model, is used. Such an object detection module can be implemented as a machine learning module. For example, the object detection module can use a fully convolutional U-Net architecture to detect target elements. The U-Net architecture is described in the paper "U-Net: Convolutional Networks for Biomedical Image Segmentation" by Olaf Ronneberger et al. (https: / / arxiv.org / abs / 1505.04597).

[0018] To detect target elements, keypoint detection can be used, for example. The target detection module can be configured for keypoint detection, i.e., detecting keypoint elements of a target structure within optical sensor data. Alternatively, other methods can be used to detect target elements. The target detection module can be configured for bounding box detection, i.e., determining bounding boxes that identify target elements of a target structure. A target element can be, for example, a portion of a target structure, or a target element can be the target structure itself. The target detection module can also be configured for segmentation mask detection, i.e., determining segmentation masks that include target elements of the target structure.

[0019] For example, an object detection module can be configured to determine a confidence level for the detection of a target element within optical sensor data. For example, the object detection module can be configured to assign a confidence level to the detected target element. The object detection module can, for example, be trained during a training phase to assign confidence levels to the detection of target elements detected within the training data. These confidence levels determined by the object detection module can, for example, be estimates trained using a loss function that quantifies the deviation of the detection of a target element from a baseline true value of the target element provided by the optical training data. The confidence level can, for example, be a function of the output of the object detection module. The maximum, minimum, mean, or integral of the output of the detection module can be examples of quantities that can be used to derive a confidence metric within a training distribution provided by multiple optical training data. Out-of-distribution confidence values ​​can, for example, be derived from the temporal stability of the output signal using the object detection module, the stability of the output signal to disturbances (such as noise), or other spatial and / or temporal characteristics of the output signal provided by the object detection module in response to receiving optical sensor data as input.

[0020] The predefined confidence threshold level achieved through the feedback loop can be, for example, a fixed value for the confidence threshold level. For instance, the feedback loop is repeated until the confidence levels of all detected target elements, the mean of the confidence levels of the detected target elements, or the confidence levels of a predefined minimum number of detected target elements reach the fixed value of the confidence threshold level. The predefined confidence threshold level to be achieved through the feedback loop can, for example, be the maximum value of the confidence threshold levels of the detected target elements. For instance, the mean of the confidence threshold levels of the detected target elements is determined, and the feedback loop is repeated, for example, until the mean reaches its maximum value.

[0021] Supervision, for example, can rely on detecting target structures (such as patient body and anatomical features and / or relevant equipment components of medical imaging systems) based on optical data (such as images) acquired using optical sensors. Reliable detection may require both high precision and high robustness.

[0022] In the scanning environment of modern medical imaging systems, lighting can be fully adapted to the individual preferences of patients and / or operators. This adaptation can be achieved not only in terms of illuminance levels, but also by the availability and application of various color schemes (e.g., to improve the environmental experience). Such features have been shown to help reduce stress for both patients and operators, and to contribute to creating a friendly and comfortable scanning environment and atmosphere.

[0023] However, lighting variations intended for adaptation can pose a challenge to object detection modules; that is, the confidence value of object element detection by the module may decrease with such changes. Object detection modules can be configured to detect object elements under specific baseline lighting conditions. However, these baseline lighting conditions are often unknown, or it may be unknown which features included in the lighting conditions have the greatest impact on the detection quality of object elements. Specifically, when a trained object detection module is trained to detect object elements using machine learning, the precise baseline lighting conditions upon which the learning is based may be unknown. For object element detection, for example, keypoint element detection (i.e., detecting keypoint features of the target structure), bounding box detection, segmentation mask detection, etc., can be used.

[0024] Even when basic lighting conditions are known, matching these basic lighting conditions to the real environment of a medical imaging system can be challenging, or it may be sufficient to adjust only individual features of the lighting conditions to achieve a sufficient level of confidence in the detection of the target element.

[0025] For example, multiple light sources can be implemented in the form of a directional colored light array including the light sources. The light sources can be provided, for example, by a set of light-emitting diodes (LEDs) and / or lasers. These light sources can include, for example, primary color light sources such as red, green, and blue. For example, the light sources can be implemented in the form of a projector (e.g., an LED or laser projector). For example, the light sources can be implemented in the form of a combination of a directional colored light array and a projector.

[0026] For example, a lower level of additional illumination may be sufficient to ensure that the confidence level reaches a predefined confidence threshold. This can be achieved, for example, through the directional characteristics of the additional illumination, the flexible selection of the color settings of the additional illumination, and / or the fact that additional illumination may be required in low-light environments. For instance, if the ambient light preference is low blue light illumination, then only a low level, localized additional green and / or red light may be needed to obtain a sufficient detection response, i.e., to achieve the confidence level required to reach the predefined confidence threshold.

[0027] Selective recovery of a predefined detection response (i.e., a confidence level reaching a predefined threshold level) can be achieved by using a feedback loop; for example, recovery only occurs when a deviation from the predefined behavior is detected. This deviation may take the form of a low response and / or a noisy response, resulting in a confidence level below the predefined threshold. For example, if a low output activation level is detected in an object detection module (e.g., including a neural network), an optimizer (e.g., a constrained optimizer) can be used to adjust the lighting conditions until a predefined threshold is reached. Alternatively, the lighting conditions can be adjusted until the maximum activation level, i.e., the maximum confidence level, is reached.

[0028] Using feedback loops may have the advantage of eliminating the need for prior knowledge about the current lighting conditions, the lighting conditions to be applied, and / or the lighting conditions to be achieved through corresponding adjustments.

[0029] Alternatively, the need to adjust illumination conditions can be determined using direct metrics derived from raw optical sensor data and / or processed optical sensor data (such as optical images). Such direct metrics may include, for example, noise level, light level, gain, and / or exposure settings.

[0030] In general, it can be assumed, for example, that even in an almost completely dark environment, it is unlikely that there will be no detection response at all. Therefore, the example can utilize additional illumination with a low duty cycle, which can also be synchronized with the actual exposure of the optical sensor.

[0031] For example, even without dedicated lighting for medical imaging systems, in most cases there will be at least some residual indirect lighting from light sources (such as monitors, control panels, indicator lights, etc.). Therefore, a detection response can be expected even without dedicated lighting.

[0032] According to another example, illumination can be smoothly and continuously adjusted at a rate different from (e.g., lower) than the frame rate of optical images provided by using an optical sensor for visualizing a medical imaging system for a human observer (e.g., an operator) until the relevant detection of the target element is completed and then the illumination can be turned off again. This approach can have the beneficial effect of reducing the irritation caused (e.g., by the patient and / or the operator of the medical imaging system lights) by the adjusted illumination (e.g., additional illumination) controlled by one or more light sources to adjust the illumination conditions.

[0033] In another example, light can be modulated at a rate higher than that perceived by humans and / or at the frame rate of the optical image provided by an optical sensor to visualize a medical imaging system for a human observer (e.g., an operator). This modulation can optionally be synchronized with the exposure rate and / or frame rate of the optical sensor, for example. This approach can have the beneficial effects of maintaining a low duty cycle, reducing interference with ambient light settings, and / or avoiding potential irritation due to perceptible flicker.

[0034] A directional color light array can be implemented, for example, by using a ring array of LEDs of alternating primary colors surrounding an optical sensor (e.g., a lens of the optical sensor), such that the illumination shadows of additional light emitted by the directional color light array may be limited. The ring array can be arranged concentrically relative to the optical sensor and / or other optics. For example, the color of different ring segments can be controlled individually. This approach can increase the controllability of illumination adjustment in terms of light level and / or color. Furthermore, individually controllable ring segments can also allow for a variety of different state indications to identify different states of the optical sensor and / or medical imaging system. State indications can, for example, include dynamic behavior in sub-regions of the array (e.g., individual ring segments) and / or the entire array.

[0035] For example, there is no need to adjust or repeat any training of the target detection module for the specific lighting conditions applied to the medical imaging system, nor is it necessary to adjust the lighting conditions of the medical imaging system to precisely match the training conditions in which the target detection module was trained.

[0036] For example, this can prevent an increase in network size and computational workload, as well as an increase in the training dataset used to train such a network.

[0037] Optical sensors can be, for example, monochromatic sensors configured to acquire optical sensor data for a single wavelength, or to acquire sensor data for a single (particularly narrow) wavelength range corresponding to a single color. For example, wavelengths corresponding to violet include the range of 380 nm to 450 nm, wavelengths corresponding to blue include the range of 450 nm to 485 nm, wavelengths corresponding to cyan include the range of 485 nm to 500 nm, wavelengths corresponding to green include the range of 500 nm to 565 nm, wavelengths corresponding to yellow include the range of 565 nm to 590 nm, wavelengths corresponding to orange include the range of 590 nm to 625 nm, and wavelengths corresponding to red include the range of 625 nm to 750 nm.

[0038] For example, the color of light captured by a monochromatic optical sensor can be invisible to the human eye, for example, in the infrared (IR) range, and especially in the near-infrared (NIR) range. Wavelengths corresponding to the NIR range include the range of 750 nm to 1400 nm (i.e., 1.4 μm). For example, a wavelength of 10 μm can be used at room temperature.

[0039] One or more light sources may be, for example, monochromatic light sources configured to emit light of the same single wavelength or light within the same single (particularly narrow) wavelength range corresponding to a single color. For example, the color of the light emitted by a monochromatic light source may be invisible to the human eye, for example, in the infrared (IR) range, and particularly in the near-infrared (NIR) range.

[0040] Using light at wavelengths invisible to the human eye can reduce the interference of lighting on ambient lighting preferences, and vice versa.

[0041] For example, the color of light collected by a monochromatic optical sensor can be that of a multicolor optical sensor, which is configured to collect light of different wavelengths corresponding to multiple colors. One or more light sources may include, for example, one or more multicolor light sources configured to emit light of multiple different wavelengths and / or a combination of multiple different monochromatic light sources configured to emit light of different wavelengths.

[0042] Illuminating a medical imaging system using multicolor light (in which a target detection module is used to detect a target) can have beneficial effects, namely, improving detection by using different color channels (i.e., wavelength dimensions). Different wavelength dimensions can, for example, improve the number of available features for the corresponding target detection. For instance, it can improve the differentiation of patients and / or objects (such as components of a medical imaging system). Therefore, compared to detection using only a single wavelength dimension (i.e., a single color of light), the corresponding detection failure rate (such as false negatives and / or false positives) can be reduced.

[0043] Generally speaking, normal lighting settings can represent statistically probable clinical use cases. These scenarios are predictable for many standard examinations using medical imaging systems, making the overall statistical performance likely to be largely determined by the optimal hardware and algorithm choices for these situations.

[0044] For example, low-light conditions can be used to operate medical imaging systems. Besides creating a comfortable environment, low-light conditions can, for example, improve the visibility of instrument and equipment displays (e.g., the displays of medical imaging systems) and provide additional illumination to the area of ​​the object being examined and / or the patient. Such additional illumination can be target-oriented and / or context-dependent. It can be adapted to the individual patient, operator, and / or work procedure.

[0045] Multiple light sources can be provided, for example, in the form of a directional color light array. The directional color light array can be attached to an optical sensor and / or configured according to the optical sensor. The elements of the directional color light array can be flexibly and individually controlled, for example, in terms of light level and / or color. The directional color light array can be used to compensate for a lack of illumination in a target area, particularly a lack of color-specific illumination characteristics.

[0046] For example, algorithms and feedback loops can be provided to detect the current lighting conditions of a medical imaging system (e.g., a room housing the medical imaging system), determine the detection response via a target detection module, and control one or more light sources such that the target element to be detected (e.g., a patient's body and / or related objects, such as components of the medical imaging system) can be illuminated independently of and without interfering with ambient lighting conditions. The illumination can be modified based on the detection response level using, for example, a constraint optimizer (such as a gradient optimizer). Constraints can be used, for example, to ensure the eye safety and comfort of the patient and / or operator.

[0047] For example, algorithms can be provided for controlling one or more light sources so that the patient's eyes are avoided and / or adjustments are provided only when needed (e.g., including additional lighting levels). For example, lighting adjustments can be provided only for individual frames.

[0048] For example, algorithms can be provided for controlling one or more light sources, enabling users (such as patients and / or operators) to immediately understand the system status and / or which functions are currently being used and / or performed; that is, to provide significant, clearly visible, flexible and detailed status indications for optical sensors and / or medical imaging systems.

[0049] For example, adjusting the trigger includes determining that the confidence value for the detection of a target element within the optical sensor data is below a predefined confidence threshold level.

[0050] If the confidence value of a target element is determined to be below a predefined confidence threshold level (i.e., the detection quality of the target element is insufficient), a feedback loop is triggered to improve the detection quality of the target element by adjusting the illumination conditions of the medical imaging system. For example, the adjustment trigger may involve determining a predefined number of confidence values ​​that are below the predefined confidence threshold level.

[0051] For example, it is determined that the confidence value for the detection of a target element within one or more spatial regions of interest (SRIOs) in optical sensor data is below a predefined confidence threshold level. This example can have the beneficial effect of ensuring improved detection quality of target elements within one or more SRIOs by adjusting the illumination conditions of the medical imaging system. Therefore, the adjustment of illumination conditions can be focused on the SRIOs. Preferably, the SRIOs are spatial regions that include the target element to be detected and / or spatial regions that are expected to include the target element to be detected.

[0052] For example, an additional control module (e.g., an AI-controlled module, such as a machine learning module) can be used to control the illumination of relevant areas of a scene detected by the additional control module using optical sensors, based on context and / or process steps. To illuminate the relevant areas determined by the additional control module, one or more control parameters can be used. For example, the additional control module can use target elements detected by a target detection module to determine the relevant areas to be illuminated.

[0053] For example, the method further includes determining quality parameters for the received optical sensor data. Adjusting the trigger includes detecting one or more of the following characteristics of the determined quality parameters: a signal-to-noise ratio level below a predefined signal-to-noise ratio level threshold, a total light intensity level below a predefined total light intensity threshold, a color-specific light intensity level below a predefined color-specific light intensity threshold, and an intensity difference between different colors of light exceeding a predefined color intensity difference threshold.

[0054] For example, the need to improve the detection quality of a target element can be indicated by detecting one or more substandard parameters in the received optical sensor data. The detection of one or more substandard parameters can serve as an adjustment trigger that initiates an improvement in the detection quality of the target element.

[0055] For example, a signal-to-noise ratio (SNR) level below a predefined SNR threshold can indicate the need to improve the detection quality of a target element. Therefore, detection of such an SNR level below the predefined threshold can be used as an adjustment trigger to activate a feedback loop to adjust illumination conditions.

[0056] For example, a total light intensity level below a predefined total light intensity threshold can indicate the need to improve the detection quality of target elements. Therefore, the detection of such a total light intensity level below the predefined total light intensity threshold can be used as an adjustment trigger to activate a feedback loop to adjust illumination conditions.

[0057] For example, a color-specific light intensity level below a predefined color-specific light intensity threshold can indicate the need to improve the detection quality of a target element. Therefore, the detection of such a color-specific light intensity level below the predefined color-specific light intensity threshold can be used as an adjustment trigger to activate a feedback loop to adjust illumination conditions.

[0058] Color-specific light intensity levels can be the intensity levels of monochromatic light or color-specific combinations of light. For example, a color-specific light intensity level can describe an absolute intensity level. Alternatively, it can describe a relative intensity level. To describe a relative color-specific light intensity level, vectors in a color space (e.g., RGB space) can be used. A predefined color-specific light intensity threshold can be described, for example, by the angle between a given first vector in the color space describing a given color-specific light intensity level and a second reference vector in the color space. If the deviation between the first vector and the second reference vector (i.e., the angle between the two vectors) is greater than a threshold angle, the color-specific light intensity level is considered to be below the predefined color-specific light intensity threshold. The second reference vector can, for example, be a mean reference vector.

[0059] For example, a reference vector c = [0.4, 0.92, 0.0] can be given in the RGB space (e.g., the region of interest). The reference vector c can be, for example, the mean vector of the color vectors in the region of interest. For example, a vector c' = [0.707, 0.707, 0.0] can be used to measure the relative color-specific light intensity level. Then, α = acos(c*c') describes the angle between the two color vectors, i.e., how much the measured vector c' deviates from the reference vector c. When the color-specific light intensity level described by c' = [0.707, 0.707, 0.0] is lower than a predefined color-specific light intensity threshold (i.e., the angle α is greater than the predefined threshold angle), an adjustment trigger for the feedback loop can be given.

[0060] For example, the need to improve the detection quality of target elements can be indicated by the intensity difference between different colors of light exceeding a predefined color intensity difference threshold. Therefore, the detection of such an intensity difference between different colors of light exceeding a predefined color intensity difference threshold can be used as an adjustment trigger to activate a feedback loop to adjust illumination conditions.

[0061] For example, quality parameters are determined for one or more spatial regions of interest within optical sensor data. This example can have the beneficial effect of triggering on-demand improvements in the quality of target element detection by detecting insufficient quality parameters in one or more spatial regions of interest. Therefore, monitoring of quality parameters can be focused on spatial regions of interest. Preferably, a spatial region of interest is a spatial region that includes the target element to be detected and / or a spatial region that is expected to include the target element to be detected.

[0062] For example, adjusting lighting conditions includes one or more of the following: increasing the total light intensity level of the lighting by one or more light sources, increasing the color-specific light intensity of the lighting by one or more light sources, or causing spatial displacement of the lighting area by one or more light sources.

[0063] For example, adjusting lighting conditions during a feedback loop involves increasing the total light intensity level of the lighting by one or more light sources.

[0064] For example, adjusting lighting conditions during a feedback loop involves increasing the color-specific light intensity of the lighting by one or more light sources.

[0065] For example, adjusting lighting conditions during a feedback loop involves spatially shifting the illuminated area by one or more light sources.

[0066] For example, the method further includes imposing one or more constraints on the adjustment of lighting conditions. These one or more constraints include one or more of the following: excluding one or more spatial segments within the optical sensor data from illumination by one or more light sources; a predefined maximum total light intensity threshold for the total light intensity of the illumination by one or more light sources; and a predefined maximum color-specific light intensity threshold for the color-specific light intensity of the illumination by one or more light sources.

[0067] Examples can have beneficial effects, as imposing constraints on the adjustment of lighting conditions can prevent harm to patients present within the medical imaging system. For instance, interference with the ambient lighting of the medical imaging system can be avoided or at least limited.

[0068] For example, constraints may include excluding one or more spatial segments within the optical sensor data from illumination by one or more light sources. Excluded spatial segments may, for example, include the patient's head, particularly the patient's eyes.

[0069] For example, constraints include a predefined maximum total light intensity threshold for illumination from one or more light sources.

[0070] For example, constraints include a predefined maximum color-specific light intensity threshold for illumination from one or more light sources.

[0071] For example, the adjustment rate of illumination conditions is lower than the predefined frame rate of the optical image provided using optical sensor data received from the optical sensor. By adjusting the illumination conditions slowly, stimulation to the patient and / or the operator of the medical imaging system can be avoided. In particular, sudden changes in illumination conditions (such as flickering) can be avoided.

[0072] For example, the adjustment rate of illumination conditions is higher than the predefined frame rate of the optical image. For instance, adjustments can be performed faster than is perceptible to the patient and / or operator. Therefore, stimulation to the patient and / or operator of the medical imaging system can be avoided or reduced. For example, adjustments can be performed at intervals. These intervals can be shorter than the reciprocal of the frame rate of the optical image, while the pauses between these intervals can be longer than the reciprocal of the frame rate of the optical image.

[0073] For example, only a few adjustments may be needed, which can be tested within a single time interval shorter than the reciprocal of the optical image frame rate. If more adjustments are required, they can be performed within one or more additional time intervals shorter than the reciprocal of the optical image frame rate.

[0074] For example, the adjustment rate is higher than 30Hz. For example, the adjustment rate is higher than 60Hz. For example, the adjustment rate is 90Hz, 120Hz, 150Hz, 180Hz or higher.

[0075] For example, the method further includes controlling the light source using one or more determined control parameters to supervise the medical imaging system using an optical sensor. By controlling the light source using one or more determined control parameters, the illumination conditions used for supervising the medical imaging system can be improved, allowing the confidence value for the detection of the target element to reach and / or exceed a predefined confidence threshold level.

[0076] For example, a light source can be controlled to continuously illuminate a medical imaging system using one or more control parameters independent of the optical sensor data acquired by the optical sensor. Continuously illuminating the medical imaging system using one or more control parameters independent of the optical sensor data acquired by the optical sensor can have the beneficial effect that, while optical sensor data is being acquired, the illumination remains unchanged because it has already been adjusted for the acquisition. Therefore, stimulation to the patient and / or the operator of the medical imaging system due to variations (especially due to sudden changes that cause flickering in the illumination) can be avoided.

[0077] For example, by using one or more control parameters accompanying the acquisition of optical sensor data by the optical sensor, the light source is controlled to synchronize the illumination of the medical imaging system with the light source. This example can have the beneficial effect that the control parameters are used to change the illumination only when needed (i.e., when acquiring optical sensor data). Thus, for example, the illumination can be changed only for the acquisition of a single frame (i.e., an image). By using the adjusted illumination only for a short period of time (e.g., faster than human perception), this adjustment may not be perceived, or at least may not be stimulating to the patient and / or the operator of the medical imaging system.

[0078] Furthermore, one or more light sources can be configured to emit status light indicating a state. For example, it can indicate the state of one or more light sources or the state of a medical imaging system.

[0079] Examples can provide clear and readily visible information about the system's activation status for various features and functions.

[0080] Examples can have the following beneficial effects: supporting the controllability of optical sensor use for the supervision of medical imaging systems based on the privacy and regulatory needs of both patients and operators. For example, the acceptance of introducing such a system can be improved by making system activity and / or status visible, allowing patients and / or operators to be alerted to the presence of optical sensors and to choose to deactivate the system when necessary. Such a system can, for example, be based on a scalable sensor and computing platform and can be designed to support a large number of potential functions and features, which can be configured via software options according to user preferences. Therefore, system status can not only be a binary value but can also indicate multiple different states of the system through various different status lights. For example, different combinations of colors of light emitted as status lights can indicate different states of the system. For example, status lights can be flashing lights. Different flashing frequencies or different combinations of flashing (e.g., for different colors of light) emitted as status lights can indicate different states of the system.

[0081] Status indication features can be independent of ambient light settings and the resulting detection response. For example, it can use the basic illumination level of a directional light array, allowing the user to always see an indication of the system's current status and / or the function currently being performed. To improve visibility in bright ambient light settings, the status indication can also be controlled via a feedback loop from the optical sensor.

[0082] A directional color light array can be implemented, for example, by using a ring array of LEDs of alternating primary colors surrounding an optical sensor (e.g., a lens of the optical sensor), such that the illumination shadows of additional light emitted by the directional color light array may be limited. The ring array can be arranged concentrically relative to the optical sensor and / or other optics. For example, the color of different ring segments can be controlled individually. This approach can increase the controllability of illumination adjustment in terms of light level and / or color. Furthermore, individually controllable ring segments can also allow for a variety of different state indications to identify different states of the optical sensor and / or medical imaging system. State indications can, for example, include dynamic behavior in sub-regions of the array (e.g., individual ring segments) and / or the entire array.

[0083] In another aspect, the present invention provides a computer program for determining one or more control parameters, the computer program including machine-executable instructions, the one or more control parameters being used to control one or more light sources to adjust the illumination conditions of a medical imaging system during the acquisition of optical sensor data using an optical sensor. The optical sensor is configured to supervise the medical imaging system. A target detection module is configured to detect target elements of one or more target structures within the optical sensor data in response to receiving optical sensor data from the optical sensor.

[0084] The processor of the computing device executes the machine-executable instructions, thereby causing the processor to control the computing device to perform a method for determining the one or more control parameters to control the one or more light sources.

[0085] The method includes receiving data from the optical sensor.

[0086] The target element within the optical sensor data is detected by using the target detection module.

[0087] A feedback loop is activated in response to receiving an adjustment trigger. The feedback loop includes: controlling the adjustment of illumination conditions of the medical imaging system using one or more light sources; receiving adjusted optical sensor data from the optical sensor for the adjusted illumination conditions; detecting the target element within the adjusted optical sensor data using the target detection module; and determining a confidence value for the detection of the target element within the adjusted optical sensor data.

[0088] The feedback loop is repeated until the confidence value determined for the detection of the target element within the adjusted optical sensor data reaches a predefined confidence threshold level. One or more adjustment parameters that define the adjustment of the lighting conditions, causing the confidence value to reach the predefined confidence threshold level, are determined as the one or more control parameters.

[0089] For example, machine-executable instructions can be configured to cause a computing device to perform any of the aforementioned method examples, the method being used to determine one or more control parameters to control one or more light sources.

[0090] In another aspect, the present invention provides a computing device for determining one or more control parameters for controlling one or more light sources to adjust the illumination conditions of a medical imaging system during the acquisition of optical sensor data using an optical sensor. The optical sensor is configured to monitor the medical imaging system. The computing device includes a target detection module configured to detect target elements of one or more target structures within the optical sensor data in response to receiving optical sensor data from the optical sensor.

[0091] The computing device includes a processor and a memory, in which machine-executable instructions are stored. The processor of the computing device executes the machine-executable instructions, thereby causing the processor to control the computing device to perform a method for determining the one or more control parameters to control the one or more light sources.

[0092] The method includes receiving data from the optical sensor.

[0093] The target element within the optical sensor data is detected by using the target detection module.

[0094] A feedback loop is activated in response to receiving an adjustment trigger. The feedback loop includes: controlling the adjustment of illumination conditions of the medical imaging system using the one or more light sources; receiving adjusted optical sensor data from the optical sensor for the adjusted illumination conditions; detecting the target element within the adjusted optical sensor data using the target detection module; and determining a confidence value for the detection of the target element within the adjusted optical sensor data.

[0095] The feedback loop is repeated until the confidence value determined for the detection of the target element within the adjusted optical sensor data reaches a predefined confidence threshold level. One or more adjustment parameters that define the adjustment of the lighting conditions, causing the confidence value to reach the predefined confidence threshold level, are determined as the one or more control parameters.

[0096] For example, a computing device can be configured to perform any of the foregoing method examples, the method being used to determine one or more control parameters to control one or more light sources.

[0097] On the other hand, the present invention provides a medical imaging system. The medical imaging system includes any of the foregoing examples of computing devices, one or more light sources configured to illuminate the medical imaging system, and an optical sensor configured to monitor the medical imaging system. The medical imaging system is one of the following: a magnetic resonance imaging system, a computed tomography system, or an X-ray imaging system.

[0098] The techniques described herein can be applied to the use of optical sensors in various medical applications, i.e., for various medical imaging systems. Medical imaging systems (e.g., MRI systems) can be included in radiotherapy (TR) systems. X-ray imaging systems can, for example, be part of image-guided therapy (IGT) systems. X-ray imaging systems can, for example, be diagnostic X-ray (DXR) systems.

[0099] It should be understood that one or more embodiments of the present invention described above can be combined, as long as the combined embodiments are not mutually exclusive.

[0100] As will be understood by those skilled in the art, aspects of the present invention can be embodied as apparatus, method, or computer program product. Therefore, aspects of the present invention can take the form of a completely hardware embodiment, a completely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, all of which may generally be referred to herein as a “circuit,” “module,” or “system.” Furthermore, aspects of the present invention can take the form of a computer program product embodied in one or more computer-readable media having computer-executable code embodied thereon.

[0101] Any combination of one or more computer-readable media can be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. As used herein, "computer-readable storage medium" encompasses any tangible storage medium capable of storing instructions that can be executed by a processor or computing system of a computing device. A computer-readable storage medium can be referred to as a computer-readable non-transient storage medium. A computer-readable storage medium can also be referred to as a tangible computer-readable medium. In some embodiments, a computer-readable storage medium can also store data accessible by a computing system of a computing device. Examples of computer-readable storage media include, but are not limited to: floppy disks, magnetic hard disk drives, solid-state drives, flash memory, USB thumb drives, random access memory (RAM), read-only memory (ROM), optical discs, magneto-optical discs, and register files of computing systems. Examples of optical discs include optical discs (CDs) and digital versatile discs (DVDs), such as CD-ROMs, CD-RWs, CD-Rs, DVD-ROMs, DVD-RWs, or DVD-R discs. The term computer-readable storage medium also refers to various types of recording media accessible by a computer device via a network or communication link. For example, data can be retrieved via a modem, via the Internet, or via a local area network. Computer-executable code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, fiber optic cable, RF, or any suitable combination thereof.

[0102] Computer-readable signal media may include propagated data signals embodying computer-executable code therein, for example, in baseband or as a carrier wave. Such propagated signals may take any of a variety of forms, including but not limited to electromagnetic, optical, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium that is not a computer-readable storage medium and may communicate, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0103] "Computer memory" or "memory" is an example of a computer-readable storage medium. Computer memory is any memory that can be directly accessed by a computing system. "Computer storage device" or "storage device" is another example of a computer-readable storage medium. A computer storage device is any non-volatile computer-readable storage medium. In some embodiments, a computer storage device may also be computer memory, and vice versa.

[0104] As used herein, "computing system" encompasses electronic components capable of executing programs or machine-executable instructions or computer-executable code. References to computing systems, including examples of "computing systems," should be interpreted as potentially encompassing more than one computing system or processing core. A computing system can, for example, be a multi-core processor. A computing system can also refer to a collection of computing systems within a single computer system or distributed across multiple computer systems. The term "computing system" should also be interpreted as potentially referring to a collection or network of computing devices, each including a processor or computing system. Machine-executable code or instructions can be executed by multiple computing systems or processors, which may be within the same computing device or even distributed across multiple computing devices.

[0105] Machine-executable instructions or computer-executable code may include instructions or programs that cause a processor or other computing system to perform one aspect of the invention. The computer-executable code for performing the operations of the aspects of the invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​(such as Java, Smalltalk, C++, etc.) and conventional procedural programming languages ​​(such as the "C" programming language or similar programming languages), and compiled into machine-executable instructions. In some cases, the computer-executable code may be in a high-level language form or a pre-compiled form, and may be used in conjunction with an interpreter that generates machine-executable instructions on the spot. In other cases, the machine-executable instructions or computer-executable code may be in a programmable gate array (GNA) form.

[0106] Computer executable code can 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 the latter case, the remote computer can 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 it can be connected to an external computer (e.g., via the Internet through an Internet service provider).

[0107] Aspects of the invention are described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block or portion of a block in a flowchart, illustration, and / or block diagram may, where applicable, be implemented by computer program instructions in the form of computer-executable code. It should also be understood that combinations of blocks in different flowcharts, illustrations, and / or block diagrams may be combined when not mutually exclusive. These computer program instructions may be provided to a computing system of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, executable via the computing system of the computer or other programmable data processing apparatus, create units for implementing the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams.

[0108] These machine-executable instructions or computer program instructions may also be stored in a computer-readable medium that can direct a computer, other programmable data processing apparatus or other device to operate in a particular manner, such that the instructions stored in the computer-readable medium produce an article of writing which includes instructions that implement functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0109] Machine-executable instructions or computer 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 apparatus or other device to produce a computer-implemented process, such that the instructions that execute on the computer or other programmable apparatus provide for implementing the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0110] The term "user interface" as used herein refers to an interface that allows a user or operator to interact with a computer or computer system. A "user interface" can also be called a "human-machine interface device." A user interface can provide information or data to and / or receive information or data from an operator. A user interface enables a computer to receive input from an operator and can provide output from the computer to the user. In other words, a user interface allows an operator to control or manipulate a computer, and the interface allows the computer to indicate the effects of the operator's control or manipulation. Displaying data or information on a monitor or graphical user interface is an example of providing information to an operator. Receiving data via a keyboard, mouse, trackball, touchpad, pointing stick, graphics tablet, joystick, game controller, webcam, headset, foot pedal, data gloves, remote control, and accelerometer are all examples of user interface components that enable the receiving of information or data from an operator.

[0111] As used herein, "hardware interface" encompasses an interface that enables a computer system to interact with and / or control external computing devices and / or devices. A hardware interface allows a computing system to send control signals or instructions to external computing devices and / or devices. A hardware interface also enables a computing system to exchange data with external computing devices and / or devices. Examples of hardware interfaces include, but are not limited to: Universal Serial Bus (USB), IEEE 1394 port, parallel port, IEEE 1284 port, serial port, RS-232 port, IEEE-488 port, Bluetooth connectivity, wireless LAN connectivity, TCP / IP connectivity, Ethernet connectivity, control voltage interface, MIDI interface, analog input interface, and digital input interface.

[0112] As used herein, “display” or “display device” encompasses an output device or user interface suitable for displaying images or data. Displays can output visual, audio, and / or tactile data. Examples of displays include, but are not limited to: computer monitors, television screens, touchscreens, tactile electronic displays, Braille screens, cathode ray tubes (CRTs), memory tubes, bistable displays, electronic paper, vector displays, flat panel displays, vacuum fluorescent displays (VFs), light-emitting diode (LED) displays, electroluminescent displays (ELDs), plasma display panels (PDPs), liquid crystal displays (LCDs), organic light-emitting diode (OLED) displays, projectors, and head-mounted displays.

[0113] The term "machine learning" (ML) refers to computer algorithms used to extract useful information from training datasets by automatically building probabilistic models (called machine learning modules or models). Machine learning modules can also be called predictive models. Machine learning algorithms build mathematical models based on sample data (called "training data") to make predictions or decisions without being explicitly programmed to perform a specific task. Machine learning modules can be implemented using learning algorithms such as supervised or unsupervised learning. Machine learning modules can be based on various techniques, such as clustering, classification, linear regression, reinforcement learning, self-learning, support vector machines, neural networks, etc. Machine learning modules can be, for example, data structures or programs such as neural networks (especially convolutional neural networks), support vector machines, decision trees, Bayesian networks, etc. Machine learning modules can be tuned, i.e., trained to predict unmeasured values. Therefore, it is possible for a trained machine learning module to predict unmeasured values ​​as outputs from other known values ​​as inputs.

[0114] The machine learning module to be trained can be, for example, an untrained machine learning module, a pre-trained machine learning module, or a partially trained machine learning module. The machine learning module being trained can be an untrained machine learning module trained from scratch. Alternatively, the machine learning module being trained can be a pre-trained or partially trained machine learning module. Generally, for example in deep learning, it may not be necessary to start with an untrained machine learning module. For example, it can start with a pre-trained or partially trained machine learning module. The pre-trained or partially trained machine learning module may have already been pre-trained or partially trained for the same or similar tasks. Using pre-trained or partially trained machine learning modules can, for example, enable faster training of the trained machine learning module to be trained, i.e., training can converge faster. For example, transfer learning can be used to train pre-trained or partially trained machine learning modules. Transfer learning refers to a machine learning process that, when solving different problems, does not learn from scratch but starts from previously learned patterns. Thus, for example, prior learning can be utilized, avoiding starting from scratch. A pre-trained machine learning module is a machine learning module that has been previously trained, for example, trained on a large benchmark dataset to solve problems similar to those to be solved through additional learning. In the case of a pre-trained machine learning module, the previous learning process has already been successfully completed. A partially trained machine learning module is one that has been partially trained, meaning the training process may not yet be complete. Pre-trained or partially trained machine learning modules can, for example, be imported and trained for the purposes disclosed herein. Attached Figure Description

[0115] In the following description, preferred embodiments of the invention will be illustrated by way of example only and with reference to the accompanying drawings, wherein: Figure 1 The illustration depicts an exemplary method for determining one or more control parameters to control one or more light sources; Figure 2 An exemplary optical sensor system including multiple light sources is illustrated; Figure 3 The illustration shows an exemplary medical imaging system environment without adjusted lighting conditions; Figure 4 The illustration shows the adjusted lighting conditions. Figure 3 An exemplary medical imaging system environment; Figure 5 The illustration depicts an exemplary computing device for determining one or more control parameters to control one or more light sources; Figure 6 The illustration shows an exemplary medical imaging system including a computing device; Figure 7 The illustration shows exemplary optical sensor training data used to train a target detection module; Figure 8 An exemplary method for training an object detection module is illustrated; Figure 9 The illustration shows an exemplary detection of a target element in optical sensor data; Figure 10 The illustration shows another exemplary detection of a target element in optical sensor data; and Figure 11 The illustration shows another exemplary detection of a target element in optical sensor data.

[0116] List of reference numerals in the attached diagram: 100 Medical Imaging System 118 patients 120 patient beds 121 Target Area 122 Target Elements 124 Materials placed on the patient's bed 125 Front Coil 126 Upper surface 128 Pad Surface 130 Vertical direction 132 Horizontal direction 140 Optical Sensor System 142 Light Source 144 Optical Sensors 152 MRI systems 154 Magnets 156 Magnet cavity 158 Imaging isocenter 160 Magnetic Gradient Coil 161 RF transmitter coil 162 Magnetic field gradient coil power supply 163 transmitter 400 computing devices 402 Calculation Component 404 memory 406 Hardware Interface 408 User Interface 410 Machine-readable instructions 412 Target Detection Module 414 Optical Sensor Data 416 Control Parameters 418 training data 500 Three-dimensional digital scale model 504 tags 520 Random Image Elements Detailed Implementation

[0117] Elements with the same numbers in these figures are equivalent elements or elements that perform the same function. If the functions are equivalent, then elements that have been discussed previously will not necessarily be discussed in the following figures.

[0118] Figure 1 An exemplary method for determining one or more control parameters for controlling one or more light sources to adjust the illumination conditions of a medical imaging system during the acquisition of optical sensor data using an optical sensor is illustrated. The optical sensor is configured to supervise the medical imaging system. A computing device for performing the method includes a target detection module configured to detect target elements of one or more target structures within the optical sensor data in response to receiving optical sensor data from the optical sensor.

[0119] In box 200, target elements within optical sensor data are detected using a target detection module.

[0120] In block 202, an adjustment trigger is received. A feedback loop is activated in response to the receipt of the adjustment trigger. The feedback loop includes blocks 204 through 212. In block 204, the adjustment of illumination conditions for the medical imaging system using one or more light sources is controlled. In block 206, adjusted optical sensor data for the adjusted illumination conditions is received from the optical sensor. In block 208, a target element within the adjusted optical sensor data is detected using a target detection module. In block 210, a confidence value for the detection of the target element within the adjusted optical sensor data is determined. In block 212, the determined confidence value for the detection of the target element within the adjusted optical sensor data is examined.

[0121] If the confidence value determined for the detection of a target element within the adjusted optical sensor data does not reach a predefined confidence threshold level, the method continues to block 204 and repeats the feedback loop. The feedback loop is repeated until the confidence value determined for the detection of a target element within the adjusted optical sensor data reaches the predefined confidence threshold level.

[0122] If the confidence value determined for the detection of a target element within the adjusted optical sensor data reaches a predefined confidence threshold level, the method proceeds to box 214. In box 214, one or more adjustment parameters that define the adjustment of the illumination conditions, causing the confidence value to reach the predefined confidence threshold level, are determined as one or more control parameters.

[0123] In box 216, one or more control parameters are defined and used to control the light source to supervise the medical imaging system using an optical sensor.

[0124] Figure 2 An exemplary light source 142 is illustrated. The light source 142 is integrated into an optical sensor system 140. In addition to the light source 142, the optical sensor system 140 also includes at least one optical sensor 144, such as a camera. The light source 142 is provided in the form of a directional color light array. The light array includes multiple elements (i.e., the light source 142), which can be flexibly and individually controlled, for example, in terms of light level and color. Such a directional color light array can be used to compensate for a lack of illumination in a target area.

[0125] A directional colored light array having a light source 142 can be implemented, for example, by using a ring array of LEDs with alternating primary colors surrounding an optical sensor 144 (e.g., a lens of the optical sensor 144), such as... Figure 2 As shown. Therefore, the illumination shadows from the additional light emitted by the directional colored light array with light source 142 may be limited. The annular array can be arranged concentrically relative to the optical sensor 144 and / or other optics. For example, the color of different annular segments can be controlled individually. This approach can increase the controllability of illumination adjustment in terms of light level and / or color. Furthermore, individually controllable annular segments can also allow for multiple different state indicators to identify different states of the optical sensor system 140 and / or the medical imaging system. State indicators can, for example, include the dynamic behavior of the array in sub-regions of the array (e.g., individual annular segments) and / or the entire array.

[0126] Figure 3 An exemplary medical imaging system environment without adjusted lighting conditions is illustrated. A patient bed 120 of a medical imaging system (e.g., a magnetic resonance imaging system) is shown. The upper surface 126 of the patient bed 120 includes a padding surface 128 on which a patient 118 lies. The front coil 125 of the magnetic resonance imaging system is arranged above the patient 118. For example, the ambient lighting can be dimmed to provide a relaxing atmosphere for the patient 118. However, low ambient lighting can cause problems for the target detection module when detecting target elements of one or more target structures. The target elements to be detected can be, for example, the ambient coil 125, the patient 118, and / or the target elements of the patient bed 120.

[0127] Figure 4 The illustration shows the adjusted lighting conditions. Figure 3An exemplary medical imaging system environment. Adjustment of illumination conditions includes additional illumination in a target area 121 (e.g., the front coil of a magnetic resonance imaging system). Within the target area 121, for example, the total illumination level is increased. For example, the adjustment of illumination conditions is constrained to prevent glare to the patient 118 by excluding the patient's head from the additional illumination. Such constraints can be used to ensure the patient's eye safety and / or comfort. Figure 4 In the exemplary case illustrated, the illumination in target region 121 (i.e., front coil 125) is improved. For example, illumination can be improved during the acquisition of a single frame of optical sensor data using an optical sensor. To determine adjustment parameters that define sufficient adjustments to the illumination conditions, the illumination in target region 121 can be modified, for example, until a sufficient detection response is achieved, i.e., until the confidence value of the detected target element within target region 121 reaches a predefined threshold. For this modification, a feedback loop can be used and, as for... Figure 1 The feedback loop is repeated as described in the method until the confidence value of the target element detected within the target region 121 reaches a predefined threshold. The resulting adjustment parameters can be used to control one or more light sources to illuminate, such as... Figure 4 The control parameters for the target area 121 are shown. Such additional lighting for the patient body 118 and other related objects 125 within the target area 121 is independent of and / or does not interfere with ambient lighting conditions.

[0128] Figure 5 An exemplary computing device 400 is illustrated for determining one or more control parameters to control one or more light sources. The computing device 400 is shown to include a computing component 402. The computing component 402 is intended to represent one or more processors or processing cores or other computing elements. The computing component 402 is shown connected to a hardware interface 406 and a memory 404. The hardware interface 406 enables the computing component 402 to exchange commands and data with other components, such as one or more light sources and / or optical sensors. The hardware interface 406, for example, enables the computing component 402 to control one or more light sources to adjust the illumination conditions of a medical imaging system, at least during the acquisition of optical sensor data using the optical sensors. The hardware interface 406, for example, also enables the computing component 402 to control the optical sensors to acquire optical sensor data. The hardware interface 406, for example, also enables the computing component 402 to control the medical imaging system.

[0129] The computing system 404 is also shown connected to a user interface 408, which, for example, enables an operator to control and operate the computing device 400 and, via the computing device 400, control and operate one or more light sources, optical sensors, and / or medical imaging systems. The user interface 408 may, for example, include output and / or input devices that enable a user to interact with the computer 400. Output devices may, for example, include a display device configured to display magnetic resonance images 426. Input devices may, for example, include a keyboard and / or mouse, enabling a user to insert control commands for controlling the computing device 400 and, via the computing device 400, control one or more light sources, optical sensors, and / or medical imaging systems.

[0130] Memory 404 is shown as containing machine-executable instructions 410. The machine-executable instructions 410 enable computing unit 402 to perform control tasks (e.g., control one or more light sources and / or optical sensors), perform numerical tasks, and perform various signal data processing tasks. The machine-executable instructions 410, for example, can enable computing unit 402 and thus computing device 400 to perform tasks according to… Figure 1 The method determines one or more control parameters to control one or more light sources to adjust the illumination conditions of the medical imaging system during the acquisition of optical sensor data using optical sensors. For example, instruction 410 may enable computing unit 402 and thus computing device 400 to control the medical imaging system.

[0131] The memory 404 is also shown to include a target detection module 412. The target detection module 412 is configured to detect target elements of one or more target structures within the optical sensor data 414 in response to receiving optical sensor data 414 from the optical sensor.

[0132] The memory 404 is also shown to contain optical sensor data 414. The optical sensor data 414 is acquired using an optical sensor configured to monitor a medical imaging system.

[0133] The memory 404 is also shown to contain one or more control parameters 416 for controlling one or more light sources to adjust the illumination conditions of the medical imaging system during the acquisition of optical sensor data using optical sensors.

[0134] The memory 404 may optionally also include training data 418, such as synthetic training data, which is configured to train the target detection module 412 to detect target elements of one or more target structures within the optical sensor data 414 in response to receiving optical sensor data 414 from the optical sensor.

[0135] Figure 6This is an exemplary medical imaging system 100 that includes a computing device 400. The computing device 400 is configured to determine one or more control parameters for controlling one or more light sources 412. Figure 6 The computing device 400 is, for example Figure 5 400 computing devices.

[0136] Medical imaging system 100 includes, for example, one or more light sources 142 configured to illuminate the medical imaging system 100 and an optical sensor 144 configured to monitor the medical imaging system 100. The optical sensor 144 is provided, for example, by an optical sensor system 140. The optical sensor system 140 may, for example, be... Figure 2 An optical sensor system 140 is implemented, which includes a light source 142 and an optical sensor 144. Medical imaging system 100 includes, for example, an exemplary magnetic resonance imaging system 152.

[0137] Alternatively, the medical imaging system 100 may include, for example, a computed tomography system or an X-ray imaging system. The medical imaging system 100 (e.g., having an MRI system 152) may be included in a radiotherapy (TR) system. The X-ray imaging system may be, for example, part of an image-guided therapy (IGT) system, or the X-ray imaging system may be, for example, a diagnostic X-ray (DXR) system.

[0138] Patient 118 is shown supported by patient bed 120. Patient bed 120 is movable in at least two spatial directions 130, 132. For example, patient bed 120 is movable in the vertical direction 130 between a lower minimum position and an upper maximum position. For example, patient bed 120 is movable in the horizontal direction 132. By moving patient bed 120 in the vertical direction 132, patient 118 lying on patient bed 120 is, for example, moved into magnet 154 of MRI system 152. For example, patient bed 120 is movable in three spatial directions.

[0139] The MRI system 152 is controlled by a computer 400. The MRI system 152 includes a magnet 154. The magnet 154 is a superconducting cylindrical magnet having a cavity 156 extending therethrough. Different types of magnets can also be used. For example, separate cylindrical magnets and so-called open magnets can also be used.

[0140] Within the cavity 156 of the cylindrical magnet 154, there exists an imaging isocenter 158 for the MRI system 152. In the imaging isocenter 158, the magnetic field is sufficiently strong and homogeneous to perform magnetic resonance imaging.

[0141] A set of magnetic field gradient coils 160 is also present within the cavity 156 of the magnet. These magnetic field gradient coils are used to acquire preliminary magnetic resonance data for spatial encoding of the magnetic spin within the cavity 156 of the magnet 154. The magnetic field gradient coils 160 are connected to a magnetic field gradient coil power supply 162. The magnetic field gradient coils 160 are intended to be representative. Typically, the magnetic field gradient coils 160 comprise three separate sets of coils for spatial encoding in three orthogonal spatial directions. The magnetic field gradient power supply 162 supplies current to the magnetic field gradient coils 160. The current supplied to the magnetic field gradient coils 160 is controlled as a function of time and can be either ramp-varying or pulse-varying.

[0142] Furthermore, the MRI system 152 may include an RF transmitter coil 161 for manipulating the orientation of magnetic spins. The RF transmitter coil 161 may also be referred to as a transmitting antenna. The RF transmitter coil 161 is connected to an RF transmitter 163. It should be understood that the RF transmitter coil 161 and the RF transmitter 163 are representative. The RF transmitter coil 161 may have multiple transmitter elements, and the RF transmitter 163 may have multiple transmitter channels.

[0143] A transmitter 163, a gradient controller 162, one or more light sources 142, and an optical sensor 144 are shown as a hardware interface 406 connected to a computer 400. The computing device 400 is intended to represent one or more computing devices. The computing device 400 is configured to acquire medical imaging data as part of a control system for a medical imaging system 100, such as acquiring MRI images using an MRI system 152. The computing device 400 is also configured to control one or more light sources 142 to adjust the illumination conditions of the medical imaging system 100 during the acquisition of optical sensor data 414 using the optical sensor 144. The optical sensor 144 is configured to monitor the medical imaging system 100.

[0144] Figure 7An exemplary optical sensor training data 418 is illustrated for training a target detection module to detect target elements 122 of a patient bed. Here, keypoint element detection is used to detect target elements 122 that exist in the form of keypoints or keypoint elements (i.e., keypoint features of the patient bed, i.e., target structures). Alternatively, other detection methods, such as bounding box detection or segmentation mask detection, can be used. The optical sensor training data 418 is synthetic training data generated using a three-dimensional digital scale model 500 of the patient bed. The three-dimensional digital scale model 500 includes an upper surface 126 having a padding surface 128. Target elements 122 in the form of keypoint elements are distributed, for example, on the upper surface 126. The target elements 122 in the form of keypoint elements are distributed, for example, circumferentially around the padding surface 128 along the contour line of the patient bed. The optical sensor training data 418 can be generated, for example, by adding random image elements 520. The random image elements 520 can be added, for example, to the background of the three-dimensional digital scale model 500. For example, random image elements 520 can also be added at least partially as random occlusions to the 3D digital scale model 500, such that at least some of the target elements 122 are covered by the random image elements 520. Therefore, the target detection module can be made robust to random occlusions, since a typical patient bed can be covered with additional materials, such as mattresses, padding, coil interfaces, and other materials.

[0145] Additionally, the optical sensor training data 418 includes labels 504 that mark the target element 122 within the optical sensor training data 418. For training the target detection module, for example, additional optical sensor training data 418 without labels 504 for the target element 122 can be provided as input to the target detection module during training. The target detection module is trained to detect the target element 122 in the provided optical sensor training data 418 without labels 504, which is identified by labels 504 in the labeled optical sensor training data 418.

[0146] For example, label 504 may include the two-dimensional horizontal coordinate values ​​of the corresponding target element 122 of the patient bed in a first coordinate system. The two-dimensional horizontal coordinate values ​​can describe the position of the corresponding target element in a plane parallel to the sensor plane of the optical sensor system. Therefore, the optical sensor training data 418 can also be used, for example, to train the target detection module to determine the two-dimensional horizontal coordinate values ​​of the labeled target element 122 of the patient bed as output.

[0147] For example, label 504 may also include a third vertical coordinate value of the corresponding target element 122 in the first coordinate system. The third vertical coordinate value describes the distance of the position of the corresponding target element 122 from the sensor plane of the optical sensor system. Therefore, the optical sensor training data 418 may also be used, for example, to train the target detection module to determine, as output, a third vertical coordinate value of the labeled target element 122 of the patient bed, in addition to the two-dimensional horizontal coordinate value.

[0148] Figure 8 The illustration depicts a method for training an object detection module to detect object elements within optical sensor data. In box 670, an object detection module to be trained is provided. In box 672, a training dataset for training the object detection module is provided. The training dataset includes optical sensor training data, and optical sensor training data in which object elements of a patient bed are labeled. Target elements may be labeled, for example, as keypoint elements. Target elements may also be identified and labeled within the optical sensor training data using bounding boxes or segmentation masks. Providing the training dataset includes, for example, generating synthetic optical sensor training data from the optical sensor training data included in the training dataset using a three-dimensional digital scale model of the patient bed. In box 674, the object detection module is trained to detect, as output, the labeled object elements of the patient bed within the optical sensor training data of the training dataset in response to receiving the corresponding training dataset.

[0149] For example, the labeled optical sensor training data may include two-dimensional horizontal coordinates of the corresponding target element of the patient bed in a first coordinate system. These two-dimensional horizontal coordinates describe the position of the corresponding target element in a plane parallel to the sensor plane of the optical sensor system. Training may also include training a target detection module to determine, in response to receiving optical sensor training data of a corresponding training dataset, the two-dimensional horizontal coordinates of the labeled target elements of the patient bed within the optical sensor training data of the training dataset as output.

[0150] For example, the label may also include a third vertical coordinate value of the corresponding target element in a first coordinate system. The third vertical coordinate value describes the distance of the corresponding target element from the sensor plane of the optical sensor system. Training may also include training a target detection module to determine, in response to receiving optical sensor training data of a corresponding training dataset, the third vertical coordinate value of the labeled target element of the patient bed within the optical sensor training data of the training dataset as output.

[0151] For example, an object detection module can be trained to determine confidence levels. These confidence levels could be, for example, estimates trained using a loss function that quantifies the deviation between the detected object element and the ground truth value of the object element provided by the optical training data. Confidence levels could also be, for example, functions of the output of the object detection module. The maximum, minimum, mean, or integral of the output of the detection module could be examples of quantities that can be used to derive confidence measures within a training distribution provided by multiple optical training data.

[0152] Figure 9 The illustration shows an exemplary detection of a target element 122 in optical sensor data 414 of a patient bed 120 using keypoint detection. The patient bed 120 is part of a medical imaging system (e.g., an MRI system). The patient bed 120 includes an upper surface 126 having a padding surface 128. The padding surface is configured for a patient to lie on. The target element 122 to be detected by the target detection module is, for example, a target element of the patient bed 120. The target element 122 in the form of keypoint elements of the patient bed 120 is, for example, distributed on the upper surface 126. The target element 122 in the form of keypoint elements of the patient bed 120 is, for example, distributed circumferentially around the padding surface 128 along the contour line of the patient bed. Additionally, additional materials 124 (e.g., mattress, padding, blanket, coil interface, and other materials) may be arranged on the patient bed 120. The target detection module is configured to detect the target element 122 in the optical sensor data 414.

[0153] Figure 10 The illustration shows another exemplary detection of target element 122 using key points detected in optical sensor data 414. Figure 9 The optical sensor data 414 includes an empty patient bed 120 of the medical imaging system 100, which has an upper surface 126 with a padding surface 128. Target elements 122, in the form of detected keypoint elements, are represented as Gaussian probability heatmaps, for example, with varying colors superimposed on the patient bed image. The sizes of the individual heatmaps allow adjacent target elements to have overlapping signal tails. Due to this overlap, a... Figure 9 The schematic diagram shows a strip structure that represents the detected target element 122.

[0154] Figure 11 The illustration shows another exemplary detection of target element 122 using key points detected in optical sensor data 414. Figure 10 The optical sensor data 414 corresponds to Figure 9 The optical sensor data is 414, the only difference is... Figure 10 The patient bed in bed 120 is not empty. Figure 10In this setting, the patient lies on patient bed 120. Additionally, extra materials 124 (e.g., mattress, padding, blanket, coil interface, and other materials) are arranged on patient bed 120. These extra materials 124 may, for example, at least partially cover some of the target elements 122. However, as... Figure 10 As shown in the schematic strip structure, the target detection module is configured to robustly detect target element 122 in optical sensor data 414.

[0155] Although the invention has been illustrated and described in detail in the accompanying drawings and the foregoing description, such illustrations and descriptions are to be considered illustrative or exemplary, and not restrictive; the invention is not limited to the disclosed embodiments.

[0156] By studying the accompanying drawings, the disclosure, and the appended claims, those skilled in the art can understand and implement other variations of the disclosed embodiments. In the claims, the word "comprising" does not exclude other elements or steps, and the quantifiers "a" or "an" do not exclude multiples. A single processor or other unit can perform the functions of several items recited in the claims. The mere fact that certain measures are recited in dissimilar dependent claims does not indicate that combinations of these measures cannot be advantageously used. Computer programs can be stored / distributed on suitable media, such as optical storage media or solid-state media supplied together with or as part of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems. Any reference numerals in the claims should not be construed as limiting the scope.

Claims

1. A method for determining one or more control parameters (416) for controlling one or more light sources (142) to adjust illumination conditions of a medical imaging system (100) during the acquisition of optical sensor data (414) using an optical sensor (144), the optical sensor (144) being configured to supervise the medical imaging system (100), and a computing device (400) for performing the method including a target detection module (412) configured to detect target elements (122) of one or more target structures within the optical sensor data (414) in response to receiving the optical sensor data (414) from the optical sensor (144). The method includes: Receive the optical sensor data (414). The target element (122) within the optical sensor data (414) is detected by using the target detection module (412). A feedback loop is activated in response to receiving an adjustment trigger, the feedback loop comprising: The medical imaging system (100) controls the adjustment of illumination conditions using one or more light sources (142), receives adjusted optical sensor data (414) from the optical sensor (144) for the adjusted illumination conditions, detects the target element (122) within the adjusted optical sensor data (414) using the target detection module (412), and determines a confidence value for the detection of the target element (122) within the adjusted optical sensor data (414). The feedback loop is repeated until the confidence value determined by the detection of the target element (122) in the adjusted optical sensor data (414) reaches a predefined confidence threshold level, and one or more adjustment parameters that cause the confidence value to reach the predefined confidence threshold level and define the adjustment of the lighting conditions are determined as the one or more control parameters (416).

2. The method according to claim 1, wherein the adjustment trigger comprises: The confidence value for the detection of the target element (122) within the optical sensor data (414) is determined to be lower than the predefined confidence threshold level.

3. The method according to claim 2, wherein the confidence value of the detection of the target element (122) within one or more spatial regions of interest in the optical sensor data (414) is lower than the predefined confidence threshold level.

4. The method according to claim 1, further comprising: Determine quality parameters for the received optical sensor data (414), wherein the adjustment trigger includes detecting one or more of the following characteristics of the determined quality parameters: signal-to-noise ratio level is lower than a predefined signal-to-noise ratio level threshold, total light intensity level is lower than a predefined total light intensity threshold, color-specific light intensity level is lower than a predefined color-specific light intensity threshold, and intensity difference between different colors of light exceeds a predefined color intensity difference threshold.

5. The method according to claim 4, wherein the quality parameter is determined for one or more spatially interested segments within the optical sensor data (414).

6. The method according to any one of the preceding claims, wherein the adjustment of the lighting conditions includes one or more of the following: increasing the total light intensity level of the lighting by one or more of the light sources (142), increasing the color-specific light intensity of the lighting by one or more of the light sources (142), and causing spatial displacement of the lighting area by one or more of the light sources (142).

7. The method according to any one of the preceding claims, further comprising: One or more constraints are imposed on the adjustment of the lighting conditions, the one or more constraints including one or more of the following: excluding one or more spatial segments in the optical sensor data (414) from the illumination by one or more of the light sources (142); a predefined maximum total light intensity threshold for the total light intensity of the illumination by one or more of the light sources (142); and a predefined maximum color-specific light intensity threshold for the color-specific light intensity of the illumination by one or more of the light sources (142).

8. The method according to any one of the preceding claims, wherein the adjustment rate of the lighting conditions is lower than the predefined frame rate of the optical image provided by using the optical sensor data (414) received from the optical sensor (144).

9. The method according to any one of claims 1 to 7, wherein the adjustment rate of the lighting conditions is higher than the predefined frame rate of the optical image.

10. The method according to claim 9, wherein the adjustment rate is higher than 30 Hz, preferably higher than 60 Hz.

11. The method according to any one of the preceding claims, wherein the method further comprises: The light source (142) is controlled by using one or more determined control parameters (416) to supervise the medical imaging system (100) by using the optical sensor (144).

12. The method of claim 11, wherein the light source (142) is controlled to continuously illuminate the medical imaging system (100) by using one or more control parameters (416) independent of the optical sensor data (414) acquired by the optical sensor (144), or By using one or more control parameters (416) in conjunction with the acquisition of optical sensor data (414) by the optical sensor (144), the light source (142) is controlled to synchronize the illumination of the medical imaging system (100) with the light source (142).

13. A computer program for determining one or more control parameters (416), the computer program comprising machine-executable instructions (410) for controlling one or more light sources (142) to adjust illumination conditions of a medical imaging system (100) during the acquisition of optical sensor data (414) using an optical sensor (144), the optical sensor (144) being configured to supervise the medical imaging system (100), and a target detection module (412) being configured to detect target elements (122) of one or more target structures within the optical sensor data (414) in response to receiving the optical sensor data (414) from the optical sensor (144). The machine-executable instructions (410) are executed by the processor (402) of the computing device (400), thereby causing the processor (402) to control the computing device (400) to perform a method including the following operations: Receive the optical sensor data (414). The target element (122) within the optical sensor data (414) is detected by using the target detection module (412). A feedback loop is activated in response to receiving an adjustment trigger, the feedback loop comprising: The medical imaging system (100) controls the adjustment of illumination conditions using one or more light sources (142), receives adjusted optical sensor data (414) from the optical sensor (144) for the adjusted illumination conditions, detects the target element (122) within the adjusted optical sensor data (414) using the target detection module (412), and determines a confidence value for the detection of the target element (122) within the adjusted optical sensor data (414). The feedback loop is repeated until the confidence value determined by the detection of the target element (122) in the adjusted optical sensor data (414) reaches a predefined confidence threshold level, and one or more adjustment parameters that cause the confidence value to reach the predefined confidence threshold level and define the adjustment of the lighting conditions are determined as the one or more control parameters (416).

14. A computing device (400) for determining one or more control parameters (416) for controlling one or more light sources (142) to adjust illumination conditions of a medical imaging system (100) during the acquisition of optical sensor data (414) using an optical sensor (144), the optical sensor (144) being configured to supervise the medical imaging system (100), the computing device (400) including a target detection module (412) configured to detect target elements (122) of one or more target structures within the optical sensor data (414) in response to receiving the optical sensor data (414) from the optical sensor (144). The computing device (400) includes a processor (402) and a memory (404) in which machine-executable instructions (410) are stored. The processor (402) of the computing device (400) executes the machine-executable instructions (410), thereby causing the processor (402) to control the computing device (400) to perform a method including the following operations: Receive the optical sensor data (414). The target element (122) within the optical sensor data (414) is detected by using the target detection module (412). A feedback loop is activated in response to receiving an adjustment trigger, the feedback loop comprising: The medical imaging system (100) controls the adjustment of illumination conditions using one or more light sources (142), receives adjusted optical sensor data (414) from the optical sensor (144) for the adjusted illumination conditions, detects the target element (122) within the adjusted optical sensor data (414) using the target detection module (412), and determines a confidence value for the detection of the target element (122) within the adjusted optical sensor data (414). The feedback loop is repeated until the confidence value determined by the detection of the target element (122) in the adjusted optical sensor data (414) reaches a predefined confidence threshold level, and one or more adjustment parameters that cause the confidence value to reach the predefined confidence threshold level and define the adjustment of the lighting conditions are determined as the one or more control parameters (416).

15. A medical imaging system (100), comprising: The computing device (400) according to claim 14 includes one or more light sources (142) configured to illuminate the medical imaging system (100) and an optical sensor (144) configured to monitor the medical imaging system (100), the medical imaging system (100) being one of the following: a magnetic resonance imaging system (152), a computed tomography system, or an X-ray imaging system.

Images