Autonomous image acquisition start / stop management system

Abstract

AUTONOMOUS IMAGING FIELD OF THE INVENTION A system and method are proposed for automatically assessing a readiness index for an autonomous scanning procedure and for continuing, pausing, or continuously assessing the imaging procedure.

Description

[Technical field]

[0001] The present invention relates to autonomous imaging. In particular, the present invention relates to a rules engine apparatus and method, an autonomous imaging system, a computer program product, and a computer readable medium for evaluating an autonomous scanning procedure for controlling an autonomous imaging device to acquire images of a patient. [Background technology]

[0002] For many medical imaging facilities, high patient throughput is crucial. Moreover, imaging will become increasingly autonomous in the future with the reduction of operator-dependent actions and automation of workflow steps to increase throughput while reducing operational costs. Summary of the Invention [Problem to be solved by the invention]

[0003] It is therefore an object of the present invention to provide an improved autonomous imaging system and method. [Means for solving the problem]

[0004] The object of the present invention is solved by the subject matter of the independent claims. Further embodiments and advantages of the present invention are incorporated in the dependent claims. Furthermore, it should be noted that, although all embodiments of the present invention relating to methods are carried out in the order of steps described, this does not necessarily have to be the only and essential order of steps of the methods presented herein. Unless otherwise stated below, the methods disclosed herein may be carried out in another order of the disclosed steps without departing from the respective method embodiments.

[0005] According to a first aspect of the present invention, there is provided a rules engine apparatus for evaluating an autonomous scanning procedure for controlling an autonomous imaging device to acquire images of a patient. The rules engine apparatus comprises an input unit, a master rule engine unit, a plurality of workflow step rule engine units, each workflow step rule engine unit being associated with a respective set of rules, and an output unit. The input unit is configured to receive a data input indicative of an event in an autonomous image acquisition workflow. The master rule engine unit is configured to select one or more workflow step rule engine units from the plurality of workflow step rule engine units for the data input to determine a set of readiness indexes, each of the selected one or more workflow step rule engine units being configured to execute one or more rules of the respective rule set in response to the data input to generate a respective readiness index indicative of a state of being ready for a particular step in the autonomous image acquisition workflow. The master rule engine unit is further configured to determine an action of the autonomous imaging device based on the set of readiness indexes. The output unit is configured to output the determined action usable for controlling the autonomous imaging device.

[0006] The inventors of the present invention have found that in an autonomous imaging system, a defined methodology should be implemented to start, stop or abort the imaging procedure. To avoid any untoward situation, more strict criteria such as patient suitability for autonomous scanning, subsequent preparation, injury prevention, subjective human intervention, etc. The inventors of the present invention have also found that in an autonomous imaging system, a well-defined procedure is needed to cover foreseen and some unforeseen circumstances.

[0007] For this purpose, a rule engine device is proposed to evaluate an autonomous scanning procedure for controlling an autonomous imaging device to acquire images of a patient. The proposed rule engine device is implemented as a "system of self-contained systems", where each self-contained system may have its own "workflow step rule engine unit" and a master rule engine unit, the output of which is a status indicating the action to be performed by the autonomous imaging device, such as "start", "stop" and "abort". The proposed rule engine device has the ability to process input data in an autonomous medical workflow setting and determine the readiness of a particular workflow step and the readiness at the autonomous scanning level.

[0008] Each self-contained system collects data from various data sources. For example, data may come from relevant sensors such as spirometers, camera-based detection mechanisms, augmented reality (AR), virtual reality (VR), physiological data sensors (e.g., Spo2 sensors, plethysmography sensors, etc.), clinical data (lung capacity, previous occurrence of any lung / cardiac disease, etc.), patient profile (athlete / swimmer), etc. Data may come from data collected from the environment in the imaging room (e.g., image data). Data may come from machine setting data (scanning protocols, etc.). These data sources are processed by various processing steps and ultimately provided as data inputs for one or more rules.

[0009] Each workflow step rule engine for real-time data processing is a kind of decision engine that evaluates data inputs according to a set of defined rules to determine a readiness index. The readiness index is a probability number between 0 and 1 or a discrete state such as "low", "medium", "high", etc. Since each rule system, rule, and processing step is self-contained, the readiness index is adjusted based on risk factors, impact, etc., for example, in the master rule engine unit.

[0010] The evaluation step for each self-contained system is a readiness index. The Master Rules Engine takes these readiness indexes to evaluate the autonomous image acquisition workflow and output an action to be taken by the autonomous imaging device, such as starting, aborting, stopping the imaging procedure, or human intervention.

[0011] The proposed rule engine apparatus also helps to improve clinical and operational efficiency across all stages of image acquisition from patient preparation to image quality assessment. The proposed rule engine apparatus helps to reduce variability and staff workload, increase productivity, and increase patient throughput. Furthermore, criteria such as patient suitability for autonomous scanning, subsequent preparation, injury prevention, subjective human intervention, etc. are reflected in a readiness index, which is provided as an input to the master rule engine unit for decision making. Thus, untoward situations are avoided.

[0012] According to one embodiment of the present invention, each rule corresponds to a particular workflow step in the autonomous image capture workflow, and the workflow steps between different rules are different.

[0013] According to one embodiment of the present invention, the master rule engine unit is configured to associate data input to at least one of the selected one or more workflow step rule engine units with a sub-step of a particular workflow step.

[0014] For example, a patient preparation workflow step may include multiple different process steps including, but not limited to, breath holding, following instructions, anxiety level, etc. Each process step may also be referred to as a sub-step of the corresponding workflow step.

[0015] According to one embodiment of the present invention, the data input includes output from a pre-trained machine learning algorithm.

[0016] In other words, some data inputs are pre-processed by a pre-trained machine learning algorithm to determine the probability of whether an event is likely to occur. The predictions from the machine learning algorithm then become inputs to the rules. The rules then evaluate the output of the machine learning model and provide an output value.

[0017] The machine learning algorithms are neural networks, support vector machines, decision trees, etc. Workflow details from previous imaging exams are used to train the machine learning algorithms.

[0018] Machine learning algorithms optimize some kind of process that cannot be completely enumerated by a set of deterministic rules.

[0019] According to one embodiment of the present invention, the multiple workflow step rule engine units are configured to update their respective rule sets using an active learning mechanism.

[0020] The process of performing a scan is very dynamic and it is difficult to determine all the conditions under which the system should abort and resume. The system and the conditions under which an event occurs are learned during every scan of the device from patient preparation to scan completion. An active learning mechanism is introduced that captures each machine state during each event and the corresponding machine state. In this process, each machine state is tagged with an event. The new state in which the abort action occurs is the new rule for the system of the system. This will be explained in detail with reference to the example shown in Figure 3.

[0021] According to one embodiment of the present invention, the data input includes one or more of data collected from a patient, data collected from a device used in an autonomous scanning procedure, data collected from an autonomous imaging device, data collected from an imaging room, and data collected from a user input.

[0022] Data entry is used, for example, to assess patient suitability for autonomous scanning, follow-up preparation, injury prevention, subjective human intervention, and the like.

[0023] For example, data collected from a patient may include, for example, sensor data, clinical data, and patient profile data.

[0024] For example, data collected from devices used in an autonomous scanning procedure may include data indicative of the status and / or functionality of devices such as electrical coils, sensors, etc.

[0025] For example, data collected from an autonomous imaging device may include data indicative of scanning protocols, operational status of the imaging device, and the like.

[0026] For example, data collected from the imaging chamber may include image data of the imaging chamber, which may be used to detect whether a foreign object approaching the imaging system interferes with the imaging procedure.

[0027] According to one embodiment of the invention, the data collected from the patient includes one or more of sensor data collected from sensors for monitoring the patient, clinical data of the patient, and patient profile data.

[0028] According to one embodiment of the present invention, the determined action includes at least one of starting image capture, pausing image capture, and stopping image capture.

[0029] According to one embodiment of the present invention, to determine an action to start image acquisition, the master rule engine unit is configured to select one or more workflow step rule engine units from the plurality of workflow step rule engine units for data input to determine a set of device-related readiness indexes indicating a state that the autonomous imaging device is ready for starting image acquisition and a set of patient-related readiness indexes indicating a state that the patient is ready for starting image acquisition.

[0030] According to one embodiment of the present invention, to determine an action to stop image acquisition, the master rule engine unit is configured to select one or more workflow step rule engine units from the plurality of workflow step rule engine units for data input to determine a set of device-related readiness indexes indicating a state in which the autonomous imaging device is not suitable for continuing image acquisition and / or a set of patient-related readiness indexes indicating a state in which the patient is not suitable for continuing image acquisition.

[0031] According to one embodiment of the present invention, to determine an action to stop image acquisition, the master rule engine unit is configured to select one or more workflow step rule engine units from the plurality of workflow step rule engine units for data input to determine a set of readiness indexes indicative of one or more of planned termination, completion of scanning protocol, image quality assessment, extent of organ of interest, and stable Internet access by the remote operator.

[0032] According to a second aspect of the present invention, there is provided an autonomous imaging system including an autonomous imaging device and a rules engine device according to the first aspect and any associated examples, wherein the autonomous imaging device is configured to acquire images of a patient based on a determined action provided by the rules engine device.

[0033] Examples of autonomous imaging devices include, but are not limited to, x-ray imagers, magnetic resonance imagers, computed tomography scanners, positron emission tomography scanners, and the like.

[0034] According to a third aspect of the present invention, there is provided a method for evaluating an autonomous scanning procedure for controlling an autonomous imaging device to acquire images of a patient, the method comprising the steps of: a) receiving, by an input unit, a data input indicative of an event in an autonomous image acquisition workflow; b) selecting, by a master engine unit, one or more workflow step rule engine units from a plurality of workflow step rule engine units for the data input to determine a set of readiness indexes, each workflow step rule engine unit being associated with a respective set of rules, and each of the selected one or more workflow step rule engine units, in response to the data input, executing the one or more rules of the respective rule set to generate a respective readiness index indicative of a state of being ready for a particular step in the autonomous image acquisition workflow; c) determining, by the master engine unit, an action for the autonomous imaging device based on the set of readiness indexes; and d) outputting, by an output unit, the determined action usable for controlling the autonomous imaging device.

[0035] According to a fourth aspect of the present invention there is provided a computer program product comprising instructions which, when executed by at least one processing unit, cause the at least one processing unit to perform steps of the method according to the third aspect and any associated examples.

[0036] According to a fifth aspect of the present invention, there is provided a computer readable medium having stored thereon a program product.

[0037] It should be understood that all combinations of the foregoing concepts and further concepts described in more detail below (provided that such concepts are not mutually inconsistent) are contemplated as part of the inventive subject matter disclosed herein. In particular, all combinations of claimed subject matter appearing at the end of this disclosure are contemplated as part of the inventive subject matter disclosed herein.

[0038] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter.

[0039] In the drawings, like reference numbers generally refer to the same parts throughout the different views. Also, the drawings are not necessarily to scale, emphasis generally being placed upon illustrating the principles of the invention. [Brief description of the drawings]

[0040] [Figure 1] FIG. 1 illustrates an exemplary rules engine apparatus 10 for evaluating an autonomous scanning procedure for controlling an autonomous imaging device to acquire images of a patient. [Diagram 2] FIG. 2 is a schematic block diagram showing the overall flow of the rules engine. [Diagram 3] FIG. 1 is a schematic block diagram illustrating an example overall workflow. [Figure 4] FIG. 1 illustrates an exemplary active learning mechanism. [Diagram 5] FIG. 1 illustrates an exemplary autonomous imaging system. [Figure 6] 1 is a flow diagram of a method for evaluating an autonomous scanning procedure for controlling an autonomous imaging device to acquire images of a patient. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0041] FIG. 1 illustrates an exemplary rules engine apparatus 10 for evaluating an autonomous scanning procedure for controlling an autonomous imaging device to acquire images of a patient. The rules engine apparatus 10 may be any computing device, including desktop and laptop computers, smartphones, tablets, and the like. The rules engine apparatus 10 may be a general-purpose device or a device having dedicated units of equipment suitable for providing the functionality described below. In the example of FIG. 1, the components of the rules engine apparatus 10 are shown as integrated into a single unit. However, in alternative examples (not shown), some or all of the components are arranged as separate modules in a distributed architecture and connected within a suitable communication network, such as a 3rd Generation Partnership Project (3GPP®) network, a Long Term Evolution (LTE) network, the Internet, a LAN (Local Area Network), a wireless LAN (Local Area Network), a WAN (Wide Area Network), and the like. The rules engine apparatus 10 and its components may be arranged as a dedicated FPGA or as a hardwired standalone chip. In some examples, the rules engine apparatus 10 or some of its components reside within a console that executes as software routines.

[0042] The rule engine apparatus 10 comprises an input unit 12, a master rule engine unit 14, a plurality of workflow step rule engine units 16, and an output unit 18. In the example shown in Fig. 1, the plurality of workflow step rule engine units 16 comprises workflow step rule engine units 16A-16N, each of which is part of or comprises an application specific integrated circuit (ASIC), electronic circuitry, processors (shared, dedicated or group) and / or memories (shared, dedicated or group), combinatorial logic circuitry, and / or other suitable components that execute one or more software or firmware programs.

[0043] The input unit 12 is configured to receive data inputs indicative of events in an autonomous image acquisition workflow. The input unit 12 is implemented in one example as an Ethernet interface, a USB™ interface, a wireless interface such as WiFi™ or Bluetooth™, or any equivalent data transfer interface that allows data transfer between input peripherals and the processing unit 14.

[0044] An event is any event that affects an autonomous imaging procedure that starts, stops, or halts the imaging process. Examples of events include, for example, events that affect patient suitability for an autonomous scan, subsequent preparation, injury prevention, subjective human intervention, etc.

[0045] In one example, vital signs (e.g., oxygen saturation, heart rate, and systolic and diastolic blood pressures) are used to assess the patient's anxiety and suitability for autonomous scanning. If the patient is determined to have a high anxiety index and a high fear index, the autonomous imaging procedure is stopped or halted. In this example, the event is that the patient has high anxiety, which affects the autonomous imaging procedure.

[0046] In one example, video signals from a video camera or depth camera monitoring the patient's facial expression or skin are used to assess the level of pain experienced by the patient. If the patient is experiencing a high level of pain, the autonomous imaging procedure is stopped to prevent or reduce physical injury. In this example, the event is that the patient is experiencing severe pain, which affects the autonomous imaging procedure.

[0047] Thus, the data input includes any data suitable for indicating that an event has occurred or may occur.

[0048] For example, the data input includes data collected from a patient.

[0049] In some examples, the data collected from the patient includes sensor data collected from one or more sensors configured to measure the patient's response before and during the autonomous imaging procedure. The sensors are used to measure, for example, the patient's movement, the patient's pain, tension, and the like. In one example, the sensor data is collected from one or more physiological data sensors that record waveforms and provide periodic measurements of vital signs such as heart rate (HR), respiration rate (RR), peripheral arterial oxygen saturation (SpO2), arterial blood pressure (ABP), and temperature (T). In another example, the sensor data is collected from a camera-based detection mechanism used to detect patient movement. In a further example, the sensor data is collected from a three-dimensional radar sensor used to monitor the movement patterns of patients, people, and devices. Radar array sensors have the advantage of creating a three-dimensional point cloud image suitable for recognition of body posture and movement, but do not allow face recognition. Radar array sensors also have the advantage of operating in any lighting condition and not being blocked by clothing or other non-conductive objects. For example, a radar array can detect a prosthetic arm or leg even when it is covered by clothing. The radar array sensor should ideally be set up in a manner that allows it to monitor the patient and the imaging room without requiring any additional action.

[0050] In some examples, the data collected from the patient further includes the patient's clinical data, such as lung capacity, any previous episodes of pulmonary or thermal illnesses, etc. Similarly, the patient profile (e.g., athlete or swimmer) is also included in the data entry. The clinical data and the patient profile are received from a hospital database.

[0051] In some examples, the data input includes data collected from devices and systems, such as machine setting data for an autonomous imaging device, such as scanning protocols, operating conditions of medical equipment, etc.

[0052] In some examples, the data input includes data collected from an imaging chamber, for example, image data used to detect whether a foreign object approaching the imaging system interferes with the imaging procedure.

[0053] In some examples, the data input includes data collected from user input, allowing for subjective human intervention, for example in the case of a medical emergency.

[0054] In some examples, the data input includes an output from a pre-trained machine learning algorithm. In other words, some data inputs are pre-processed by a pre-trained machine learning algorithm to determine the probability of whether an event may occur. The prediction from the machine learning algorithm then becomes the input to the rules. The rules then evaluate the output of the machine learning model and provide an output value. The machine learning algorithm optimizes some kind of process that cannot be fully enumerated by a set of deterministic rules. For example, a machine learning algorithm is used to correlate facial expressions in image data with anxiety levels. In this example, instead of directly providing the image data as a data input for one or more rules, the image data is first pre-processed by a machine learning algorithm and the output of the machine learning algorithm, i.e., the determined anxiety level, is provided to one or more rules. The machine learning algorithm can be a neural network, a support vector machine, a decision tree, etc. Workflow details from previous imaging examinations are used to train the machine learning algorithm.

[0055] The master rule engine unit 14 is configured to select one or more workflow step rule engine units from the plurality of workflow step rule engine units 16 for the data input to determine a set of readiness indexes. Each of the selected one or more workflow step rule engine units 16 is configured to execute one or more rules 20 of a respective rule set in response to the data input to generate a respective readiness index indicative of a state of readiness for a particular step in the autonomous image capture workflow.

[0056] In other words, the proposed rule engine device 10 is implemented as a "system of self-contained systems", where each self-contained system can have its own "workflow step rule engine unit" and a master rule engine unit, whose outputs are states indicating actions to be performed by the autonomous imaging device, such as "start", "stop" and "abort". A state called "resume" is similar to a state called "start".

[0057] Figure 2 shows a schematic block diagram showing the overall flow of the rule engine. As shown in Figure 2, each self-contained system includes a workflow step rule engine unit 16 and a self-contained rule system 20. Each self-contained system operates based on defined rules for a particular segment of the autonomous image acquisition workflow. In other words, each workflow step rule engine 16 for real-time data processing is a kind of decision engine that evaluates data inputs according to a set of defined rules to determine output values.

[0058] For example, the workflow step rules engine 16A receives data inputs from one or more data sources 24, such as data source A and data source B shown in Figure 2. The data inputs include data collected from patients, devices, systems, imaging rooms, and / or user inputs, as described above.

[0059] The master rule engine unit 14 is configured to select one or more workflow step rule engine units 16 from a plurality of workflow step rule engine units 16, such as units 16A-16N shown in FIG. 2, for data input to determine a set of readiness indexes. As shown in FIG. 2, the one or more rules 20 include a plurality of processing steps. For example, a patient preparation workflow step includes a plurality of different processing steps, including but not limited to holding breath, following instructions, anxiety level, etc. Each processing step is also referred to as a sub-step of the corresponding workflow step.

[0060] The evaluation step for each self-contained system is a readiness index. For each workflow step, the rule engine unit 16 evaluates data from various sources and provides a readiness index. As explained above, some rules include multiple processing steps. For example, rule 20A includes processing steps 22A and 22B. For example, in the patient preparation workflow step described above, one of the readiness indexes is a "patient readiness index" that focuses on whether the patient is ready for scanning in an autonomous setting. This index has different readiness indexes and corresponding rule engine settings. Exemplary readiness indexes include, but are not limited to, a "breath-hold readiness index," a "command-following index," an "anxiety index," and a "metal object risk index."

[0061] Some readiness indices are probability numbers between 0 and 1. Some readiness indices are discrete states, such as "low," "medium," or "high."

[0062] Returning to Figure 1, the master rules engine unit 14 takes all these readiness indexes, as described above, evaluates the autonomous image capture workflow, and outputs actions to be performed by the autonomous imaging device via the output unit 18. The determined actions can be used to control the autonomous imaging device.

[0063] The output unit 18 is implemented in one example as an Ethernet interface, a USB™ interface, a wireless interface such as WiFi™ or Bluetooth™, or any equivalent data transfer interface that allows data transfer between output peripherals and the processing unit 14.

[0064] 3 shows a schematic block diagram illustrating an example overall workflow 50. For purposes of illustration, the example autonomous image acquisition workflow is broadly divided into six specific workflow steps: readiness checklist, start scan prompt, event alert cancellation, end scan prompt, image assessment, and termination.

[0065] In the first workflow step 52, i.e., the readiness checklist, one or more workflow step rule engine units are provided to evaluate data from one or more data sources and provide one or more readiness indexes, such as a patient readiness index indicating the patient's readiness for scanning in an autonomous setting and a device readiness index indicating the system's readiness for scanning in an autonomous setting.

[0066] In this workflow step, the data input includes data collected from the patient. In some examples, the data includes sensor data obtained from one or more sensors measuring the patient's response. For example, the sensor data includes image data obtained from monitoring the patient's movements prior to the scanning procedure and vital signs obtained from monitoring the patient's anxiety level prior to the scanning procedure. In some examples, if the imaging procedure requires a contrast agent, the data input further includes data indicating whether the contrast agent has been injected. In some examples, if the imaging procedure requires anesthesia or a sedative, the data input further includes data indicating whether the patient has been administered anesthesia or a sedative. Additionally, the data input includes the patient's identification information, data indicating whether a metal object is present in the body, and pre-existing conditions such as pregnancy, allergies, medications, etc., collected from the hospital database. These data inputs are used to determine whether the patient is ready for the start of the scan. Thus, the multiple workflow step rule engine unit 16 is used to provide different readiness indexes such as "anxiety index", "sedation index", "contrast agent index", "metal object risk index", and "patient condition risk index".

[0067] In some examples, the data inputs include data collected from devices and systems. For example, the data inputs include data indicative of a scan protocol selection result, data indicative of a coil selection result, data indicative of a medical equipment work status, data indicative of a device disinfection has been performed, data indicative of a stress test of a remote VPN connection to a remote operator, data indicative of a camera system status and position, data indicative of a balance of patient support, and data indicative of a cardiac gating probe placement. These data inputs are used to determine whether the devices and systems are sufficiently prepared for the start of a scan. Thus, the multiple workflow step rule engine unit 16 is used to provide different readiness indexes, such as a "coil readiness index", a "scan protocol readiness index", a "medical equipment readiness index", a "camera system readiness index", a "VPN connection readiness index", a "patient support readiness index", and a "cardiac gating probe placement readiness index".

[0068] In some examples, the data input includes user-input data, such as patient identification, obtained through a user interface. Examples of user interfaces employed in various implementations of the present disclosure include, but are not limited to, switches, potentiometers, buttons, dials, sliders, trackballs, display screens, various types of graphical user interfaces (GUIs), touch screens, microphones, cameras, and other types of sensors that receive some form of human-generated stimulus and generate a signal in response thereto. Thus, user-input data allows for subjective human intervention.

[0069] In some examples, the data input includes data collected from one or more sensors monitoring the environment in the scanner room. The sensor data includes, for example, devices present in the scanner room that generate noise or image artifacts, and video signals from a video camera monitoring whether the scanner room door is closed. These data inputs enable the system to determine whether the environment in the scanner room is suitable for starting conditions. Therefore, multiple workflow step rule engine units are used to provide different readiness indexes, such as an "object risk index" and a "scanner room readiness index."

[0070] The master rules engine unit 14 then obtains the exemplary readiness index described above to evaluate the autonomous image capture workflow and determine whether to initiate a scan (block 54).

[0071] When the imaging procedure begins, one or more workflow steps associated with the workflow step "Canceling Event Alert" rule engine unit 16 evaluates data inputs and determines, based on these data inputs, whether a top priority emergency mechanism is required (block 56).

[0072] In some examples, the data input includes data collected from the patient. For example, the data includes sensor data obtained from one or more sensors measuring the patient's response. The sensor data includes image data obtained from monitoring the patient's movement, vital signs obtained from monitoring the patient's anxiety and medical emergency, data obtained from a sedation monitoring device to monitor early emergence from sedation, and / or data obtained from monitoring the level of pain experienced by the patient. In some examples, a video feed with a field of view covering the body part of interest received from a combination of various three-dimensional non-contact motion scanners using, for example, light detection and ranging (LIDAR), radio detection and ranging (RADAR), and camera-based sensors at different positions is used to measure one or more of the patient's movement, the patient's pain, and tension. Thus, multiple workflow step rule engine units are used to provide different readiness indexes, such as a "pain index," an "anxiety index," a "sedation index," and a "medical emergency index." For each readiness index, a threshold level is set to determine whether the scanning procedure needs to be stopped.

[0073] In some examples, the data input includes user input data obtained via a user interface, for example, via an integrated emergency button integrated into the MRI scanner or a command to abort the scanning procedure received from a remote operator. The user input data thus allows for subjective human intervention. For example, a patient may press an integrated emergency button in case of pain and anxiety. Thus, the multiple workflow step rules engine unit 16 is used to provide different readiness indexes, such as a "patient intervention index" and an "operator intervention index".

[0074] In some examples, the data input includes data collected from various devices and systems. For example, the data input includes data indicative of the status of the electrical coil, the location of the sensor, the location of the mattress within the imaging system, and / or the status of the Internet connection to a remote client. Thus, the data input enables the system to determine, for example, whether the status and functionality of the imaging device, the system, and the Internet connection are sufficient to proceed with the autonomous imaging procedure. Thus, multiple workflow step rule engine units are used to provide different readiness indexes, such as an "electrical coil status index," a "sensor location index," a "mattress location index," and an "Internet connection index."

[0075] In some examples, the data inputs include data collected from one or more sensors monitoring the environment in the scanner room. The sensor data includes video signals from video cameras monitoring objects brought into or near the scanner room during imaging and / or the patient's relatives in the scanner room. These data inputs enable the system to detect whether objects and / or people interfere with the scanning process. Thus, the one or more workflow step rules engine unit 16 provides different readiness indexes, such as an "object interference index" and a "person interference index".

[0076] The exemplary readiness index described above is then provided to the master rules engine unit 14 to determine whether to abort the imaging procedure.

[0077] If the imaging procedure is not aborted, one or more workflow step rule engine units associated with the workflow step "End Scan Prompt" evaluate the data inputs and determine whether to stop the imaging procedure based on these data inputs (step 58). The data inputs include data indicating the planned end, data indicating the completed scanning procedure, data indicating the extent of the organ of interest, and data indicating stable Internet access by the remote operator. Thus, multiple workflow step rule engine units are used to provide different readiness indexes such as "Planned End Index", "Scanning Procedure Completed Index", "Organ Extent Index", "Internet Connection Index", etc.

[0078] Once the imaging procedure is stopped, one or more workflow step rule engine units associated with the workflow step "Image Assessment" evaluate the image data and determine, based on these data inputs, whether another scan needs to be performed (step 60).

[0079] If the image quality meets a predetermined criteria, the autonomous imaging procedure ends (step 62).

[0080] It will be appreciated that because each of the rule engine systems, rules, and processing steps are self-contained, the exemplary readiness indexes described above are individually adjusted based on risk factors and impacts, for example, in the master rule engine unit.

[0081] The process of performing a scan is very dynamic and it is difficult to determine all the conditions under which the system should abort and resume. The system and the conditions under which an event occurs are learned during every scan of the device from patient preparation to scan completion. An active learning mechanism is introduced that captures each machine state during each event and the corresponding machine state. In this process, each machine state is tagged with an event. The new state in which the abort action occurs is the new rule for the system of the system.

[0082] 4 shows an exemplary active learning mechanism. In this example, if the system is unable to take the correct action (block 70), the scan, machine, patient, and environment conditions captured during the scan (block 72) are provided as feedback to update the initial set of rules (block 74). The updated rules (block 76) are then used as new rules for the system to output states (block 78) such as "start", "stop", "abort", "resume", and "continue". Furthermore, since the system is unable to take the correct action (block 70), user intervention (block 80) is required, for example to stop or abort the scanning procedure. After the rules are updated, the scanning procedure is resumed.

[0083] 5 illustrates an example autonomous imaging system 100 including the above-described autonomous imaging device 90 and the rules engine device 10. The autonomous imaging device 90 is configured to acquire images of a patient based on determined actions provided by the rules engine device 10.

[0084] Examples of autonomous imaging device 90 include, but are not limited to, x-ray imagers, magnetic resonance imagers, computed tomography scanners, positron emission tomography scanners, and the like.

[0085] 5, the rules engine unit 10 is a separate device configured to communicate with the autonomous imaging device 90 through a wireless and / or wire-based interface. However, in alternative examples, the rules engine unit 10 resides within the autonomous imaging device 90, for example, executing as a software routine.

[0086] 6 illustrates a flow diagram of a method 200 for evaluating an autonomous scanning procedure for controlling an autonomous imaging device to acquire images of a patient. The method is performed by the exemplary device shown in FIG.

[0087] In step 210, ie step a), a data input is received via an input unit of the exemplary device 10, indicating an event in an autonomous image capture workflow.

[0088] As described in detail above, data inputs include data collected from the patient, from the device and autonomous imaging equipment, from the imaging room, and / or from user inputs that are used to assess patient suitability for autonomous scanning, subsequent readiness, injury prevention, subjective human intervention, etc.

[0089] In step 220, i.e., step b), the master engine unit selects one or more workflow step rule engine units from the plurality of workflow step rule engine units for the data input to determine a set of readiness indexes. Each workflow step rule engine unit is associated with a respective set of rules. Each of the selected one or more workflow step rule engine units is configured to execute one or more rules of the respective rule set in response to the data input to generate a respective readiness index indicating a state of being ready for a particular step in the autonomous image acquisition workflow. For example, in the patient preparation stage, the master rule engine selects one or more workflow step rule engine units associated with patient preparation to determine a set of readiness indexes.

[0090] In some examples, each rule corresponds to a specific workflow step in the autonomous image acquisition workflow, and the workflow steps between different rules are different. The master rule engine unit is configured to associate data input to at least one of the selected one or more workflow step rule engine units with sub-steps of the specific workflow step. For example, in a patient preparation step, the multiple workflow step rule engine units are used to provide different readiness indexes, such as "anxiety index", "sedation index", "contrast index", "metal object risk index", and "patient condition risk index". These workflow steps are also referred to as sub-steps of the patient preparation workflow step.

[0091] In step 230, i.e., step c), the master engine unit then determines an action for the autonomous imaging device based on the set of readiness indexes, the determined action including one or more of starting image capture, ceasing image capture, and stopping image capture.

[0092] To determine an action to start image acquisition, the master rule engine unit is configured to select one or more workflow step rule engine units from the multiple workflow step rule engine units for data input to determine a set of device-related readiness indexes indicating a state that the autonomous imaging device is ready for the start of image acquisition and a set of patient-related readiness indexes indicating a state that the patient is ready for the start of image acquisition.

[0093] To determine an action to stop image acquisition, the master rule engine unit is configured to select one or more workflow step rule engine units from the plurality of workflow step rule engine units for data input to determine a set of device-related readiness indexes indicating a state in which the autonomous imaging device is not suitable for continuing image acquisition and / or a set of patient-related readiness indexes indicating a state in which the patient is not suitable for continuing image acquisition.

[0094] To determine an action to stop image acquisition, the master rule engine unit is configured to select one or more workflow step rule engine units from the plurality of workflow step rule engine units for data input to determine a set of readiness indexes indicative of one or more of planned termination, completion of scanning protocol, image quality assessment, extent of organ of interest, and stable Internet access by the remote operator.

[0095] In step 240, ie, step d), the output unit of the exemplary device 10 outputs the determined actions usable to control the autonomous imaging device.

[0096] All definitions and those used herein should be understood to supersede any dictionary definitions, definitions in documents incorporated by reference, and / or ordinary meanings of the defined terms.

[0097] As used in this document in the specification and claims, the indefinite articles "a" and "an" should be understood to mean "at least one," unless otherwise specified.

[0098] The term "and / or" as used herein in the specification and claims should be understood to mean "either or both" of the elements so conjoined, i.e., elements that are conjunctive in some cases and disjunctive in other cases. Multiple elements listed with "and / or" should be construed in the same manner, i.e., "one or more" of the elements so conjoined. Other elements are optionally present other than the elements specifically identified by the "and / or" clause, whether related or unrelated to the elements specifically identified.

[0099] As used herein in the specification and claims, the phrase "at least one" in reference to a list of one or more elements should be understood to mean at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of every element specifically listed in the list of elements, and not excluding any combination of elements in the list of elements. This definition also allows for the optional presence of elements other than those specifically identified in the list of elements to which the phrase "at least one" refers, whether related or unrelated to the specifically identified elements.

[0100] In another exemplary embodiment of the invention, a computer program or a computer program element is provided, characterized in that it is adapted to execute, on a suitable system, the method steps of the method according to one of the previous embodiments.

[0101] Thus, a computer program element is stored on a computing unit which is also part of an embodiment of the present invention. This computing unit is adapted to execute or direct the execution of the steps of the method described above. Furthermore, the computing unit is adapted to operate the components of the apparatus described above. The computing unit may be adapted to operate automatically and / or to execute user instructions. The computer program is loaded into the working memory of a data processor. The data processor is thus equipped to execute the method of the present invention.

[0102] This exemplary embodiment of the invention covers both computer programs that use the invention from the beginning and computer programs that, through updates, turn existing programs into programs that use the invention.

[0103] Moreover, the computer program element is capable of providing all the steps required for carrying out the procedures of the exemplary embodiments of the methods described above.

[0104] According to a further exemplary embodiment of the present invention, a computer readable medium, such as a CD-ROM, is presented, having stored thereon computer program elements, which are described in the previous section.

[0105] The computer program may be stored and / or distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless communication systems.

[0106] However, the computer program may also be presented via a network such as the World Wide Web and downloaded from such a network into the working memory of a data processor. According to a further exemplary embodiment of the invention, a medium for making a computer program element downloadable is provided, the computer program element being configured to perform a method according to one of the aforementioned embodiments of the invention.

[0107] Although several embodiments of the invention have been described and illustrated herein, those skilled in the art will readily envision various other means and / or structures for performing the functions and / or obtaining one or more of the results and / or advantages described herein, and each such variation and / or modification is deemed to be within the scope of the inventive embodiments described herein. More generally, those skilled in the art will readily appreciate that all parameters, dimensions, materials, and configurations described herein are meant to be exemplary, and that the actual parameters, dimensions, materials, and / or configurations will depend on the particular application or applications in which the teachings of the invention are used. Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many equivalents to the specific inventive embodiments described herein. It is therefore to be understood that the foregoing embodiments have been presented by way of example only, and that within the scope of the appended claims and their equivalents, the inventive embodiments may be practiced otherwise than as specifically described and claimed. The inventive embodiments of the present disclosure are directed to each individual feature, system, article, material, kit, and / or method described herein. Furthermore, any combination of two or more such features, systems, articles, materials, kits, and / or methods is included within the inventive scope of the present disclosure, if such features, systems, articles, materials, kits, and / or methods are not mutually inconsistent.

Claims

1. 1. A rules engine apparatus for evaluating an autonomous scanning procedure for controlling an autonomous imaging device to acquire images of a patient, the rules engine apparatus comprising: An input unit; A master rule engine unit; a plurality of workflow step rule engine units, each workflow step rule engine unit being associated with a respective set of rules, each rule corresponding to a particular workflow step in the autonomous image acquisition workflow, the workflow steps between different rules being different; Output unit and Equipped with the input unit receiving a data input indicative of an event in the autonomous image capture workflow; the master rule engine unit selects one or more workflow step rule engine units from the plurality of workflow step rule engine units for the data input to determine a set of readiness indexes, and each of the selected one or more workflow step rule engine units executes one or more rules of the respective rule set in response to the data input to generate a respective readiness index indicative of a state of being prepared for a particular step in the autonomous image capture workflow; the master rule engine unit further determines an action for the autonomous imaging device based on the set of readiness indexes; A rules engine apparatus, wherein the output unit outputs the determined action usable to control the autonomous imaging device.

2. The rules engine apparatus of claim 1 , wherein the master rules engine unit associates the data input to at least one of the selected one or more workflow step rules engine units with a sub-step of the particular workflow step.

3. The rules engine apparatus of claim 1 or 2, wherein the data input comprises output from a pre-trained machine learning algorithm.

4. The rule engine apparatus according to claim 1 , wherein the plurality of workflow step rule engine units update their respective rule sets using an active learning mechanism.

5. The data input is data collected from said patient; Data collected from devices used in the autonomous scanning procedure; data collected from the autonomous imaging device; Data collected from the imaging room, and Data collected from user input 5. A rules engine apparatus according to claim 1, comprising one or more of:

6. The data collected from the patient includes: sensor data collected from a sensor for monitoring the patient; Clinical data of the patient; and Patient Profile Data The rules engine apparatus of claim 5 , comprising one or more of:

7. The determined action is Initiating image acquisition; Stopping image acquisition, and Stopping image acquisition The rules engine device according to claim 1 , further comprising at least one of:

8. 8. The rule engine apparatus of claim 7, wherein to determine the action to start image acquisition, the master rule engine unit selects one or more workflow step rule engine units from the plurality of workflow step rule engine units for the data input to determine a set of device-related readiness indexes indicating a state that the autonomous imaging device is ready for starting image acquisition and a set of patient-related readiness indexes indicating a state that the patient is ready for starting image acquisition.

9. 8. The rule engine apparatus of claim 7, wherein to determine the action to stop image acquisition, the master rule engine unit selects one or more workflow step rule engine units from the plurality of workflow step rule engine units for the data input to determine a set of device-related readiness indexes indicating a state in which the autonomous imaging device is not suitable for continuing image acquisition and / or a set of patient-related readiness indexes indicating a state in which the patient is not suitable for continuing image acquisition.

10. To determine the action of stopping image acquisition, the master rule engine unit selects one or more workflow step rule engine units from the plurality of workflow step rule engine units for the data input; Planned termination, Completion of the scanning protocol, Image quality assessment, The extent of the organ of interest, and Stable Internet access by remote operators 8. The rules engine apparatus of claim 7, further comprising: a set of readiness indexes indicative of one or more of:

11. An autonomous imaging device; The rule engine device according to any one of claims 1 to 10. wherein the autonomous imaging device acquires images of a patient based on determined actions provided by the rules engine device.

12. 1. A method for evaluating an autonomous scanning procedure for controlling an autonomous imaging device to acquire images of a patient, the method comprising: a) receiving, by an input unit, a data input indicative of an event in an autonomous image capture workflow; b) selecting, by a master engine unit, for the data input, one or more workflow step rule engine units from a plurality of workflow step rule engine units to determine a set of readiness indexes, where each workflow step rule engine unit is associated with a respective set of rules, each rule corresponding to a particular workflow step in the autonomous image capture workflow, workflow steps between different rules being different, and where each of the selected one or more workflow step rule engine units, in response to the data input, executes one or more rules of the respective rule set to generate a respective readiness index indicative of a state of being ready for a particular step in the autonomous image capture workflow; c) determining, by the master engine unit, an action for the autonomous imaging device based on the set of readiness indexes; d) outputting, by an output unit, the determined actions usable for controlling the autonomous imaging device. The method comprising:

13. A computer program comprising instructions which, when executed by at least one processing unit, cause the at least one processing unit to perform the steps of the method according to claim 12.

14. A computer readable medium storing the program according to claim 13.

Images