Automated detection scanning inspection

Abstract

Disclosed herein is a medical system (100, 300, 400) comprising a memory (110) storing machine executable instructions (120). The medical system further comprises an anatomy detection module (122). The anatomy detection module is configured for detecting an anatomical deviation in response to input tomographic medical scout image data (124). The anatomy detection module is configured for outputting a scout (126) of the anatomical deviation in tomographic medical scout image data if the anatomical deviation is detected. The medical system further comprises a processor (104) configured for controlling the medical system. Execution of the machine executable instructions causes the processor to receive (200) tomographic medical scout image data, receive (202) the scout of the anatomical deviation from the anatomy detection module in response to inputting the tomographic medical scout image data into the anatomy detection module, and provide (204) a warning signal (128) if the scout is received.

Description

Technical Field

[0001] This invention relates to medical imaging, and more particularly to scan planning for tomographic medical imaging modalities. Background Technology

[0002] In computed tomography (CT) medical imaging modalities such as magnetic resonance imaging (MRI) or computed tomography (CT), the internal anatomical structures of an object can be imaged. During the CT medical imaging process, the region of interest to be imaged is typically located using a so-called scout scan or locator scan. Scout scans are acquired at low resolution and / or with a high signal-to-noise ratio to quickly locate the region of interest. After the region of interest has been located in the acquired scout scan, the operator or automated algorithm then configures the medical imaging system to acquire more detailed clinical scans.

[0003] U.S. Patent Application US2017 / 0293734 discloses a system for identifying significant incidental discoveries from medical records. In one exemplary embodiment, an exemplary computing device receives a medical report and derives a text portion from the report. The computing device then identifies one or more medical discoveries from the text portion and determines a clinical context for each of the discoveries. The computing device then identifies one or more clinical clues from the discoveries and generates one or more condition signals based on those clues. The computing device then generates a condition alert based on the condition signals. The condition alert indicates a significant incidental discovery. Using various embodiments contemplated herein, significant follow-up discoveries can be identified for a user.

[0004] US 2018 / 0268569 A1 relates to a method and apparatus for detecting abnormalities in medical imaging data of a patient's region outside the region to be examined. The abnormality information may also include information on additional assessment measures (i.e., additional medical examinations) that should be initiated in response to the identified abnormality.

[0005] US 2019 / 0320934 A1 relates to automated sequence prediction in medical imaging sessions using deep learning. Abnormal (tissue) areas in a patient can be identified within MR data.

[0006] Actions within the scanning chamber trigger the inspection equipment to examine the object and obtain the inspection results. The document also discloses notifying the object that he or she may leave the scanning chamber once image acquisition is complete. Summary of the Invention

[0007] The present invention provides medical systems, computer program products, and methods in the independent claims. Embodiments are given in the dependent claims.

[0008] Reconnaissance scans, also described herein as tomographic medical image data, are used to locate the region from which clinical tomographic medical image data is acquired. Reconnaissance scans will have lower resolution and / or a lower signal-to-noise ratio than clinical tomographic medical image data, allowing for rapid acquisition. Reconnaissance medical image data is also acquired for a first region, and clinical tomographic medical image data is acquired for a second region. The second region is within the first region. Therefore, the reconnaissance medical image data images anatomical structures not located within the second region. If anatomical abnormalities exist within the first region but outside the second region, they may go unnoticed. The quality of the reconnaissance medical image data may be insufficient for a human to ultimately assess any anatomical abnormalities.

[0009] The embodiments may provide an improved medical system using an anatomical detection module, which can be used to automatically detect and locate anatomical abnormalities in tomographic medical reconnaissance image data. For example, such a system can be used to examine large volumes of reconnaissance images and detect anatomical abnormalities that would be difficult for humans to detect. For instance, differences in the relative size of organs may not be noticeable to humans. In other examples, tumors, hyperplasia, or other irregularities may be excessively masked by noise or undetectable due to low resolution.

[0010] In one aspect, the present invention provides a medical system including a memory storing machine-executable instructions. The medical system also includes an anatomical detection module. The anatomical detection module may, for example, be software or a machine-executable component also stored in the memory. In other examples, the anatomical detection module may be a sophisticated or independent computing device. The anatomical detection module is configured to detect anatomical deviations in response to input tomographic medical reconnaissance image data. The detection includes locating the anatomical deviations in the output tomographic medical reconnaissance image data. The tomographic medical reconnaissance image data may, for example, be two-dimensional or three-dimensional image data.

[0011] Tomographic medical reconnaissance image data may also have lower resolution than images used to provide diagnosis or diagnostic images. For example, the localization of anatomical deviations may be an indication of the location of the anatomical deviation. In some paradigms, this may be the location containing at least a portion of the anatomical deviation; in others, it may be a segmentation or bounding box. Anatomical deviations may, for example, be growths or structures that are not part of a normal object. For example, tumor growths may be an example of anatomical deviations. In other paradigms, anatomical deviations may be anatomical structures whose size, location, or boundaries deviate from a particular normal range. For example, an organ may have irregular boundaries; it may be able to have additional structures or growths within it. Anatomical deviations may also indicate that the size of a particular organ or anatomical region is larger or smaller than would be expected with respect to other anatomical structures within the object.

[0012] The medical system also includes a processor configured to control the medical system. In various examples, the medical system can take different forms. In some examples, the medical system can be a computing device, such as a workstation used by medical professionals to examine radiological data. In other examples, the medical system can be a component that may be located remotely or in the cloud providing processing of medical image data. In yet another example, the medical system may also include a computed tomography medical imaging system or a scanner.

[0013] The execution of machine-executable instructions enables the processor to receive computed tomography (CT) medical reconnaissance image data. This reception can occur in different ways across various paradigms. In some paradigms, the CT medical reconnaissance image data can be retrieved from storage devices that are part of the medical system. In other paradigms, the CT medical reconnaissance image data can be received via a network connection or via an external data carrier. In yet another paradigm, the CT medical imaging system can be controlled to receive the CT medical reconnaissance image data.

[0014] The execution of machine-executable instructions also enables the processor to receive anatomical deviations from the anatomical detection module in response to inputting tomographic medical localization data into the anatomical detection module.

[0015] The execution of machine-executable instructions also enables the processor to provide a warning signal upon receiving a location. This warning signal can take different forms in different paradigms. In some paradigms, the warning signal can be a display or indicator on the screen of the medical system itself. For example, the medical system could be a terminal or workstation controlling a tomographic medical imaging system. In this case, the warning signal can alert the operator that an anatomical deviation has been detected in one of the tomographic medical reconnaissance image data. This allows the operator of the medical system to quickly determine whether further scanning is needed. For example, this can be beneficial to operators who are not trained to view tomographic medical reconnaissance image data. Moreover, in large systems acquiring large amounts of data, it may be impractical or impossible for the operator of the medical system to do so because of the acquisition of tomographic medical reconnaissance image data.

[0016] In another embodiment, the medical system further includes a tomographic medical imaging system configured to acquire medical imaging data from an imaging region. The memory also includes medical imaging system control commands configured to control the tomographic medical imaging system to acquire the tomographic medical reconnaissance image data.

[0017] The execution of the machine-executable instructions also enables the processor to control the computed tomography (CT) medical imaging system to acquire computed tomography reconnaissance image data by utilizing medical imaging system control commands. The execution of the machine-executable instructions also enables the processor to receive clinical scan planning data in response to acquiring the computed tomography reconnaissance image data. The computed tomography reconnaissance image data describes a first region. The clinical scan planning data is configured to modify the medical imaging system control commands to acquire clinical computed tomography image data describing a second region. The second region is within the first region. The clinical computed tomography image data has a higher resolution and / or a higher signal-to-noise ratio than the computed tomography reconnaissance image data. The clinical computed tomography image data may be acquired, for example, using different acquisition protocols.

[0018] The execution of machine-executable instructions also enables the processor to construct clinical control commands by modifying medical imaging system control commands using clinical scan planning data. Furthermore, the execution of machine-executable instructions allows the processor to control the medical imaging system to acquire clinical tomographic imaging data using these clinical control commands.

[0019] This embodiment can be beneficial for examining low-resolution tomographic medical reconnaissance image data. If an automated system is used to examine medical image data acquired by a tomographic medical imaging system, technicians will first use higher-resolution data for inspection. This embodiment can provide the benefit of detecting anatomical deviations in tomographic medical reconnaissance image data that are generally considered useless for detecting anatomical errors.

[0020] In another embodiment, the computed tomography medical imaging system is a magnetic resonance imaging system.

[0021] In another embodiment, the tomographic medical imaging system is a computed tomography system.

[0022] In another embodiment, the tomographic medical imaging system is a combination of computed tomography and positron emission tomography.

[0023] In another embodiment, the computed tomography medical imaging system is a combination of a magnetic resonance imaging system and a positron emission tomography system.

[0024] In another embodiment, the execution of machine-executable instructions also causes the processor to receive a random scan indicator in response to providing a warning signal. The random scan indicator provides a choice between a discharge recipient selector and a random scan selector. The random scan indicator is a control or flow indicator that causes a change in the behavior of the processor in the medical system. The random scan indicator may, for example, be a variable or indicator that allows selection between the discharge recipient selector and the random scan selector.

[0025] If an additional scan indicator selects the discharge recipient selector, the execution of machine-executable instructions also causes the processor to provide a discharge recipient signal after completing the acquisition of clinical computed tomography medical imaging data. In some examples, a discharge recipient signal may also be provided if no warning signal is provided. The discharge recipient signal may be, for example, a display or indicator on the medical system, or it may be a light indicator, bell, or other indicator that can be used to signal the recipient. The operator of the medical system can use the discharge recipient signal to notify the imaged recipient that he or she can leave.

[0026] If the incidental scan indicator provides an incidental scan selector, the execution of machine-executable instructions also causes the processor to receive incidental scan planning data. This part may operate in several different ways. For example, an automated system may be used to provide incidental scan planning data. For instance, this positioning may be used to set up a set of planes or areas for automated scanning using a computed tomography medical imaging system. In other examples, a user interface or dialog box may be presented to an operator of the medical system, who can input incidental scan planning data into the medical imaging system's user interface. In still other examples, incidental scan planning data may be attached to the incidental scan indicator. For example, if the incidental scan indicator has already been received from a different workstation or remote location, the automated system or a medical professional may have already attached incidental scan planning data to it.

[0027] In some examples, if the third region is located within the edge region or part of the first region, the machine-executable instructions can be configured to acquire additional tomographic medical reconnaissance image data. For example, the machine-executable instructions can be configured to select an additional field of view for the additional tomographic medical reconnaissance image data, such that the third region is located within the central area of ​​the additional field of view.

[0028] In some examples, this additional tomographic medical reconnaissance image data can also be forwarded to a selected computing device.

[0029] In another embodiment, the execution of the machine-executable instructions further enables the processor to construct incidental control commands by modifying medical imaging system control commands using incidental scan planning data. The execution of the machine-executable instructions also enables the processor to control the medical imaging system using the incidental control commands to acquire incidental tomographic medical imaging data. This embodiment may be advantageous because it provides the acquisition of incidental tomographic medical imaging data.

[0030] In another embodiment, incidental scan planning data describes a third region. The third region is at least partially located within the first region. The third region does not intersect with the second region at least partially.

[0031] In some embodiments, the third region may include the region indicated by the location of anatomical deviations received from the anatomy detection module.

[0032] In another embodiment, the execution of the machine-executable instructions further causes the processor to send a warning signal to a selected computing device via a network connection. In this case, the warning signal may include additional data. In some examples, the warning signal may also include anatomical deviations and tomographic medical investigation image data. The execution of the machine-executable instructions also causes the processor to receive a stray scan indicator from the selected computing device via a network connection in response to sending the warning signal to the selected computing device. This embodiment may be advantageous, for example, because it can be used to contact remote systems or individuals to provide stray scan indicators.

[0033] The selected computing device can take different forms. In one example, it could be a smartphone. In other examples, it might be a computer or workstation used in a radiology department. In yet another example, it could be a computer system located in various locations. The computer system could be a desktop computer.

[0034] In another embodiment, the execution of machine-executable instructions causes a warning signal to be sent to a selected computing device before the acquisition of clinical tomographic medical imaging data is completed. This can be advantageous because it can provide the opportunity to provide further imaging of the subject before the subject has been discharged from the hospital.

[0035] In another embodiment, the medical system further includes a selected computing device. The selected computing device includes a display. The selected computing device is configured to automatically display a warning signal upon receipt. For example, the processor of the medical system can push the warning signal to the selected computing device, and this can override other operations of the computing device, thereby immediately drawing the operator's attention.

[0036] In another embodiment, the memory includes a list of permitted computing devices. The execution of machine-executable instructions also causes the processor to poll permitted computing devices for the current user activity. The current user activity may be, for example, an indication of when a device or computing device was last used. The current user activity may also indicate the use of permitted computing devices. The execution of the machine-executable instructions also causes the processor to select a chosen computing device from the permitted computing devices by applying predetermined selection criteria to the current user activity. This can be particularly advantageous for timely receipt of incidental scan indicators. For example, the list of permitted computing devices may be a list of permitted computing devices belonging to or operated by a specific physician. This, for example, allows physicians to be contacted more quickly and enables incidental scan indicators to be received before the patient has been discharged.

[0037] In other examples, the list of permitted computing devices could be computing devices used by various medical professionals or physicians. This allows the medical system to automatically contact currently available physicians or medical professionals. Predefined selection criteria can also enable the system to contact physicians currently engaged in activities for which interference would be acceptable. For example, if the permitted computing device is a smartphone, the predetermined selection criteria could allow viewing one or more apps currently being used by the smartphone. If the physician is currently checking emails or using a leisure time app, the predetermined selection criteria could automatically determine whether to issue a warning signal to that particular computing device.

[0038] Another concrete example would be if the permitted computing device is a specific workstation in a radiology department. If that workstation is currently being used by a radiologist to examine other medical imaging data, the system could be configured to automatically interrupt what the physician or healthcare professional is currently doing and provide a warning signal on the selected computing device. This would not only allow for faster reception of incidental scan indicators but also minimize disruption to the workflow of the specific healthcare professional or physician.

[0039] In another embodiment, the anatomical detection module includes a segmentation algorithm. This segmentation algorithm is adapted to detect anatomical deviations. For example, the segmentation algorithm can be used to detect whether the boundary between two anatomical regions is irregular or deformed. This can be used to trigger a warning signal, and the region triggering the warning signal can also be used to provide a locator. In other examples, this may also trigger a warning signal if the segmentation indicates that a particular anatomical region is larger than expected or proportionally larger. The segmentation algorithm can also detect anatomical structures that are not present in a particular model or anatomical atlas and are therefore outside the scope of the segmentation algorithm. This may also trigger a warning signal.

[0040] In another embodiment, the anatomical detection module includes a neural network. The neural network is configured to output the localization of anatomical deviations in response to receiving a tomographic medical reconnaissance scan. For example, the neural network can be trained to view tomographic medical reconnaissance image data and provide a warning signal when an anatomical deviation is detected. For example, the neural network can be a convolutional neural network. The neural network can be trained using various reconnaissance scans that do not contain anatomical deviations as well as some reconnaissance scans that do contain anatomical deviations. This can include various proliferative or abnormal structures. It can also include tomographic medical reconnaissance scans that have specific anatomical structures in the wrong location and / or are disproportionate to other anatomical structures.

[0041] In another embodiment, the neural network is a so-called U-net neural network. Using a U-net neural network can be advantageous because it is able to correlate data across different spatial scales. This can be particularly useful for detecting the presence of anatomical biases and performing image segmentation.

[0042] In another aspect, the present invention provides a computer program product comprising machine-executable instructions and an anatomical detection module. The machine-executable instructions are configured to be executed by a processor controlling a medical system. The anatomical detection module is configured to detect anatomical deviations in response to input tomographic medical reconnaissance image data and to output the location of the anatomical deviation in the tomographic medical reconnaissance image data. The execution of the machine-executable instructions causes the processor to receive the tomographic medical reconnaissance image data.

[0043] The execution of machine-executable instructions also enables the processor to receive the location of anatomical deviations from the anatomical detection module in response to inputting computed tomography medical reconnaissance image data into the anatomical detection module. The execution of machine-executable instructions also enables the processor to provide warning signals.

[0044] In another aspect, the present invention provides a method for training the neural network. The method includes receiving training data. The training data includes training tomographic medical reconnaissance image data. The training data also includes labels. The labels identify the location of anatomical deviations in the training tomographic medical reconnaissance image data. The method further includes training the neural network using the labeled training data according to a deep learning algorithm.

[0045] It should be understood that one or more of the foregoing embodiments of the present invention can be combined, as long as the combined embodiments are not mutually exclusive.

[0046] As those skilled in the art will recognize, various aspects of the present invention can be implemented as apparatus, method, or computer program product. Accordingly, various 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 be referred to herein as "circuit," "module," or "system" in general). Furthermore, various aspects of the present invention can take the form of a computer program product implemented in one or more computer-readable media having computer-executable code implemented thereon.

[0047] Any combination of one or more computer-readable media can be used. The computer-readable media 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 executable by a processor of a computing device. A computer-readable storage medium may be referred to as a computer-readable non-transient storage medium. A computer-readable storage medium may also be referred to as a tangible computer-readable medium. In some embodiments, a computer-readable storage medium may also be capable of storing data accessible by a processor 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 disks, magneto-optical disks, and processor register files. Examples of optical disks include compact discs (CDs) and digital universal 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 on a modem, the Internet, or a local area network. Computer-executable code implemented 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.

[0048] Computer-readable signal media may include propagated data signals having computer-executable code implemented therein, for example, in baseband or as a carrier wave. Such propagated signals may take any 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 is capable of conveying, propagating, or transmitting a program used by or in conjunction with an instruction execution system, apparatus, or device.

[0049] "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 processor. "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, or vice versa.

[0050] As used herein, the term "processor" encompasses electronic components capable of executing programs or machine-executable instructions or computer-executable code. References to computing devices including "processor" should be interpreted as capable of containing more than one processor or processing core. A processor may, for example, be a multi-core processor. A processor may also refer to a collection of processors within a single computer system or distributed across multiple computer systems. The term computing device should also be interpreted as capable of referring to a collection or network of computing devices, each comprising one or more processors. Computer-executable code can be executed by multiple processors, which may be within the same computing device or even distributed across multiple computing devices.

[0051] Computer executable code may include machine-executable instructions or programs that cause a processor to perform aspects of the present invention. Computer executable code for performing operations related to aspects of the present invention may be written in any combination of one or more programming languages ​​and compiled into machine-executable instructions, 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. In some instances, the computer executable code may be in the form of a high-level language or in a pre-compiled form and used in conjunction with an interpreter that generates machine-executable instructions in flight.

[0052] The computer-executable code may be executed 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 may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet provided by an Internet service provider).

[0053] Aspects of the invention are described with reference to flowchart illustrations, diagrams, and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that, when applicable, each block or portion of a flowchart illustration, diagram, and / or block diagram can be implemented by computer program instructions in the form of computer-executable code. It should also be understood that combinations of blocks from different flowchart illustrations, diagrams, and / or block diagrams can be combined when not mutually exclusive. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus that produces the machine, such that the instructions, executable via the processor of the computer or other programmable data processing apparatus, create units for implementing the functions / actions specified in the flowchart illustrations and / or one or more block diagram blocks.

[0054] These computer program instructions may also be stored in a computer-readable medium that can instruct 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 that includes instructions that implement the functions / actions specified in flowcharts and / or one or more block diagrams.

[0055] The 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, thereby producing a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide a process for the function / action specified in the flowchart and / or one or more block diagram boxes.

[0056] As used herein, a "user interface" is an interface that allows a user or operator to interact with a computer or computer system. A "user interface" can also be referred to as a "human-machine interface device." A user interface can provide or receive information or data from an operator. A user interface enables input from an operator to be received by the computer and output from the computer to the user. In other words, the user interface allows an operator to control or manipulate the computer, and the interface allows the computer to indicate the effects of the operator's control or manipulation. The display of data or information on a monitor or graphical user interface is an example of providing information to an operator. The reception of data via a keyboard, mouse, trackball, touchpad, pointing stick, graphics tablet, joystick, game controller, webcam, headset, pedal, wired gloves, remote control, and accelerometer are all examples of user interface components that implement the reception of information or data from an operator.

[0057] As used herein, "hardware interface" encompasses the interface that enables a computer system's processor to interact with and / or control external computing devices and / or devices. A hardware interface can allow the processor to send control signals or instructions to external computing devices and / or devices. A hardware interface can also enable the processor 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.

[0058] 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.

[0059] In this context, tomographic medical image data is defined as two-dimensional or three-dimensional data acquired using a medical imaging scanner. A medical imaging scanner is defined herein as a device suitable for acquiring information related to a patient's physical structure and constructing a two-dimensional or three-dimensional medical image dataset. Tomographic medical image data can be used to construct visualizations useful for physician diagnosis. This visualization can be performed using a computer. Both tomographic medical reconnaissance image data and clinical tomographic image data are examples of tomographic medical image data. Attached Figure Description

[0060] Preferred embodiments of the invention will be described below by way of example only and with reference to the accompanying drawings, in which:

[0061] Figure 1 The illustration shows an example of a medical system;

[0062] Figure 2 The illustrated operation is shown. Figure 1 A flowchart of a medical system paradigm;

[0063] Figure 3 The illustration shows another example of a medical system;

[0064] Figure 4 The illustration shows another example of a medical system;

[0065] Figure 5 The illustration shows another example of a medical system;

[0066] Figure 6 The illustration shows another example of a medical system; and

[0067] Figure 7 A flowchart illustrating another example of the medical system in operation is shown.

[0068] List of reference numerals in the attached diagram:

[0069] 100 Medical Systems

[0070] 102 Computer

[0071] 104 processor

[0072] 106 Hardware Interfaces

[0073] 108 User Interface

[0074] 110 Memory

[0075] 120 Machine-executable instructions

[0076] 122 Anatomical Detection Module

[0077] 124-fold tomography medical investigation image data

[0078] 126 Localization of Anatomical Deviation

[0079] 128 Warning Signs

[0080] 130 monitor

[0081] 132 Warning message

[0082] 200 received computed tomography (CT) medical investigation image data

[0083] 202 The localization of anatomical deviations is received from the anatomical detection module in response to input from the computed tomography medical detection module.

[0084] 204 If location is received, a warning signal is provided.

[0085] 300 Medical System

[0086] 302 Tomography Medical Imaging System

[0087] 304 Imaging Area

[0088] 306 Object

[0089] 308 Object Support

[0090] 310 First District

[0091] 312 Second Area

[0092] 314 Third District

[0093] 320 Medical Imaging System Control Commands

[0094] 322 Clinical Scan Planning Data

[0095] 324 Clinical Tomography Medical Imaging Data

[0096] 400 Medical System

[0097] 402 Magnetic Resonance Imaging System

[0098] 404 magnet

[0099] 406 Magnet Chamber

[0100] 410 Magnetic Gradient Coil

[0101] 412 Magnetic field gradient coil power supply

[0102] 414 Radio Frequency Coil

[0103] 416 transceiver

[0104] 420 Accidental Scan Indicator

[0105] 422 Accidental Scan Planning Data

[0106] 424 Accidental Control Command

[0107] 426 Incidental Tomography Medical Imaging Data

[0108] 428 Automated Scanning Planning Module

[0109] 500 network connection

[0110] 502 Smartphone

[0111] 504 Mobile computing devices

[0112] 506 workstation

[0113] 508 desktop computer

[0114] 510 List of permitted computing devices

[0115] 600 Selected computing devices

[0116] 602 User Interface

[0117] 604 Change Message

[0118] 606 Immediate Review Button

[0119] 608 Reject Review Button

[0120] 610 Permitted Computer Equipment

[0121] 700 Collection and reconnaissance scanning.

[0122] 702 Perform scan planning

[0123] 704 Image Acquisition

[0124] 706 was detected during the reconnaissance scan.

[0125] 708 Assess the need for additional scans.

[0126] 710 Remote assessment of reconnaissance scanning

[0127] 712 Information regarding the operator Detailed Implementation

[0128] Elements with similar numbers in these figures are either equivalent or perform the same function. If they are functionally equivalent, elements already discussed will not need to be discussed in later figures.

[0129] Figure 1 An example of a medical system 100 is illustrated. The medical system 100 is shown as including a computer 102. In this example, the medical system 100 is a workstation. Alternatively, the medical system 100 in this example could also be a remote server or processor in the cloud for processing medical image data.

[0130] Computer 102 is shown as including processor 104. Processor 104 is intended to represent one or more processing cores at one or more locations. Processor 104 may be distributed among multiple computers 102 that may be in different locations. Processor 104 is shown as being connected to an optional hardware interface 106. Hardware interface 106 may, for example, be used to control other components of medical system 100. Processor 104 is also connected to an optional user interface 108. Processor 104 is also connected to memory 110. Memory may be any memory or storage device accessible to processor 104.

[0131] Memory 110 is shown as containing machine-executable instructions 120. Machine-executable instructions 120 contain instructions that enable processor 104 to perform basic data and image processing tasks, and may also control other components of medical system 100 via hardware interface 106. Memory 110 is also shown as containing an anatomical detection module. The anatomical detection module is configured to detect anatomical deviations in response to input tomographic medical reconnaissance image data. If an anatomical deviation is detected, the anatomical detection module is configured to output the location of the anatomical deviation within the tomographic medical reconnaissance image data.

[0132] Memory 110 is also shown as containing sectional medical reconnaissance image data 124. Memory 110 is also shown as containing anatomical deviation 126 within the sectional medical reconnaissance image data 124, which is obtained by inputting the sectional medical reconnaissance image data 124 into the anatomical detection module 122. The location of anatomical deviation 126 may be, for example, a location specified within the sectional medical reconnaissance image data 124. In other examples, it may be a segmentation. In response to receiving the location of anatomical deviation 126, a warning signal 128 has been generated. The warning signal 128 can be used to trigger various actions. In this example, user interface 108 is shown as including display 130. A warning message 132 is placed on display 130 to indicate to the operator that an anatomical deviation has been detected.

[0133] Figure 2 The illustrated operation is shown. Figure 1 The flowchart describes a method for a medical system. The method begins at step 200. In step 200, computed tomography medical reconnaissance image data 124 is received. Next, in step 202, the computed tomography medical reconnaissance image data 124 is input into an anatomical detection module 122. If the anatomical detection module 122 detects an anatomical deviation, it outputs the location of the anatomical deviation 126. In response, the processor 104 then generates a warning signal 128 in step 204.

[0134] Figure 3 This illustrates another example of Medical System 300. Medical System 300 and... Figure 1 It is similar to the medical system 100, except that it additionally includes a tomography medical imaging system 302. Figure 3 The tomographic medical imaging system 302 is intended to be representative. For example, it may be a magnetic resonance imaging system, a computed tomography system, a combined computed tomography and positron emission tomography system, or even possibly a combined magnetic resonance imaging system and positron emission tomography system.

[0135] The tomographic medical imaging system includes an imaging region 304. The imaging region 304 is the area in space where the medical system 302 can measure medical imaging data. An object 306 is shown resting on an object support 308. The object 306 is at least partially within the imaging region 304. Within the imaging region 304 are a first region 310, a second region 312, and a third region 314. The first region 310 corresponds to the region where tomographic medical reconnaissance image data 124 is acquired. The memory 110 also contains medical imaging system control commands 320, which can be used to control the tomographic medical imaging system 302 to acquire medical imaging data from any of the three locations 310, 312, or 314. In some examples, the third region 314 may extend beyond the first region 310.

[0136] Processor 104 can be configured to calculate clinical scan planning data 322. This can be modified to acquire clinical tomographic medical imaging data 324 from a second region 312. A third region 313 can represent a region of object 306. The location of anatomical deviation 126 can, for example, include the coordinates or position of the third region 314. In response to receiving tomographic medical reconnaissance image data 124, clinical scan planning data 322 can be generated. For example, clinical scan planning data 322 can be manually entered into user interface 108, or it can be generated using automated algorithms or neural networks. Clinical scan planning data 322 can be used to modify medical imaging system control commands 320 to acquire clinical tomographic medical imaging data 324.

[0137] Figure 4 The illustration shows another example of a medical system 400. Figure 4 The example shown in the diagram is the same as Figure 3 The examples shown in the diagram are similar, except that the computed tomography medical imaging system 302 is specifically a magnetic resonance imaging system 402.

[0138] The magnetic resonance imaging system 402 includes a magnet 404. Magnet 404 is a superconducting cylindrical magnet with a bore 406 passing through it. It is also possible to use different types of magnets; for example, it may use both split cylindrical magnets and so-called open magnets. A split cylindrical magnet is similar to a standard cylindrical magnet, except that the cryostat has been divided into two parts to allow access to the equiplanar plane of the magnet; for example, such a magnet can be used with charged particle beam therapy. An open magnet has two magnet sections, one above the other, with a sufficiently large space in between to receive the object: the arrangement of the two sections is similar to that of a Helmholtz coil. Open magnets are preferred because the object is less confined. An assembly of superconducting coils is located inside the cryostat of the cylindrical magnet.

[0139] An imaging region 304 exists within the bore 406 of a cylindrical magnet 404, where the magnetic field is sufficiently strong and uniform to perform magnetic resonance imaging. In this example, the first region 310, the second region 312, and the third region 324 can be considered regions of interest (ROIs). Acquired magnetic resonance data are typically acquired for the ROI.

[0140] A set of magnetic field gradient coils 410 is also present within the bore 406 of the magnet, which is used to acquire preliminary magnetic resonance data for spatial encoding of the magnetic spin within the imaging region 408 of the magnet 404. The magnetic field gradient coils 410 are connected to a magnetic field gradient coil power supply 412. The magnetic field gradient coils 410 are intended to be representative. A typical magnetic field gradient coil 410 contains three independent sets of coils for spatial encoding in three orthogonal spatial directions. The magnetic field gradient power supply supplies current to the magnetic field gradient coils. The current supplied to the magnetic field gradient coils 410 is controlled as a function of time and can be either slanted or pulsed.

[0141] Adjacent to the imaging region 304 is an RF coil 414 for manipulating the orientation of magnetic spins within the imaging region 304 and for receiving radio transmissions from spins also located within the imaging region 304. This RF antenna may comprise multiple coil elements. The RF antenna may also be referred to as a channel or antenna. The RF coil 414 is connected to an RF transceiver 416. The RF coil 414 and the RF transceiver 416 may be replaced by separate transmit and receive coils and separate transmitters and receivers. It should be understood that the RF coil 414 and the RF transceiver 416 are representative. The RF coil 414 is also intended to represent a dedicated transmit antenna and a dedicated receive antenna. Similarly, the transceiver 416 may also represent separate transmitters and receivers. The RF coil 414 may also have multiple receive / transmit elements, and the RF transceiver 416 may have multiple receive / transmit channels. For example, if a parallel imaging technique such as SENSE is performed, the RF coil 414 may have multiple coil elements.

[0142] Transceiver 416 and gradient controller 412 are shown as hardware interface 106 connected to computer system 102.

[0143] In this example, the medical imaging system control command is a pulse sequence command, and both the clinical tomography medical imaging data 324 and the tomography medical reconnaissance image data 124 are magnetic resonance images.

[0144] The memory is also shown to include a random scan indicator 420. This may have been received, for example, via user interface 108 or via a network connection. The memory 110 is also shown to contain random scan planning data 422. This can be used, for example, to acquire random tomographic medical imaging data 426 from a third region 314. In some cases, the random scan planning data 422 can be entered manually. In other cases, it can be generated by an automated scan planning module 428.

[0145] Figure 5 It shows Figure 3Another view of the medical system 300. The medical system 300 can also be replaced by a medical system 400. In this example, the medical system 300 is connected to various computing devices, such as a smartphone 502, a mobile computing device 504, a workstation 506, and a desktop computer 508, via a network interface 500. These devices 602, 604, 606, and 608 are examples of permitted computer devices 610. For example, they can be work devices or personal computing devices of medical professionals or physicians. When the medical system 300 detects an anatomical deviation and provides a warning signal 128, the medical system 300 can forward the warning signal to one of the devices 502, 504, 506, and 508. In response, it can receive an incidental scan indicator 420 from one of the devices.

[0146] In some examples, medical system 300 may poll each of the permitted computing devices 610 to determine current user activity. Devices 502, 504, 506, and 508 can be selected from the permitted computing devices 610 using predetermined selection criteria. For example, this could allow for faster response times and more efficient use of time by physicians or healthcare professionals using one of the devices.

[0147] Figure 6 Another view of smartphone 502 is shown. When the warning signal is generated by medical system 300, the system determines that the physician owning smartphone 502 is currently using email. In response, medical system 300 sends a warning signal to smartphone 502. In this case, smartphone 502 is the selected computing device 600. This then causes an alarm message 604 to be displayed on the user interface 602 of smartphone 502. For example, two buttons are then presented, one is a "Review Now" button 606 and the other is a "Refuse Review" button 608. If the "Review Now" button 606 is pressed, data describing the reconnaissance scan and providing location information is displayed on the user interface 602. Thus, the physician or healthcare professional can then provide a random scan indicator 420. In some instances, the random scan indicator 420 may simply indicate whether a third area is scanned. In other instances, it may provide more detailed instructions on how to perform further scans.

[0148] When performing an MRI scan, such as on the lumbar spine, a localization or locator scan (e.g., T1-weighted low-resolution scan; three orthogonal planes) is initially acquired and used to plan the geometry of the diagnostic images. Reconnaissance scans may reveal incidental findings, such as renal tumors or aortic aneurysms, which are not properly visualized in the diagnostic images (e.g., due to field of view). Typically, incidental findings go undetected after the scan phase until the study is interpreted. Occasionally, findings are not even detected because they are only visible on low-resolution and often overlooked reconnaissance images. As a result, either incidental findings are missed, or if detected, the patient must be invited for another scanning session.

[0149] Examples can combine one or more of the following features:

[0150] 1. Design an MR scan card that includes: 1) higher contrast and / or spatial resolution, which provides improved sensitivity for identifying incidental findings on reconnaissance scans; and 2) improved spatial coverage, which enhances the chance of including common incidental findings (e.g., kidney, aorta, ovary).

[0151] 2. Detect the category of incidental findings in MR reconnaissance scans (e.g., kidney, aorta, ovary) (using methods such as neural networks or model-based approaches) and determine the potential need for additional MR series, and

[0152] 3. In cases of potential need for additional MR scans, trigger rapid two-way communication between the radiologist and the automatically generated reconnaissance images (e.g., directly in person or via remote / cloud-based means (e.g., remote radiography)) for review of the images while the patient is still on the MR scanner, thus enabling additional scans.

[0153] 4. Notify the MR scanner operator via message whether the patient can be released, whether the decision regarding additional MR series is pending, or whether additional scans should be performed, and

[0154] 5. Automatically initiate additional MR series acquisitions when needed.

[0155] Steps 2 and 3 are performed after the acquisition of the reconnaissance scan during the remainder of the MR scan, so that incidental findings may be detected before the patient leaves the MR kit if additional imaging is acquired (if appropriate, at the same setting).

[0156] The Exemplary Medical System can be integrated with MR scanner consoles or other tomographic imaging system consoles.

[0157] MRI of the lumbar spine is one of the most common MRI examinations required, second only to brain MRI. Typically, this study is read by a radiologist, and usually by a neuroradiologist or musculoskeletal radiologist. As is typical of many imaging examinations, a lumbar spine MRI is often an examination in which, once completed, no surgical disease is found, either medical intervention including pharmacological and / or non-pharmacological treatments (such as physical therapy) is provided to the patient, or no treatment is offered. In either case, a lumbar spine MRI may be the only advanced imaging procedure that can be performed (although conventional X-ray imaging is also commonly performed).

[0158] Occasionally, incidental findings are disclosed on lumbar MRI scans, and the radiologist is the gatekeeper at this point. If the findings are insignificant, they are rarely included in the reported findings. If an incidental finding is more significant, such a finding is usually listed in the impression (conclusion) of the imaging report and is typically reported to the referring physician / provider by phone, text, or other means. Unfortunately, if the examination results are not observed and reported, and if the lumbar MRI proves to be the only examination performed during the work period, it is possible that incidental findings (e.g., kidney / ureteral tumors, abdominal aortic aneurysms, ovarian masses, adrenal masses, etc.) will be allowed to progress: i.e., missed opportunity situations.

[0159] Therefore, it would be helpful to establish a system that increases the chances of positive results, thereby enabling incidental lesions to 1. be detected, 2. be reported, and 3. be acted upon, providing the best chance for a good outcome for the patient, even if otherwise a significant health threat is discovered incidentally. Even more helpful would be a system that allows for automated detection and reporting to the radiologist while the patient is still undergoing the examination, so that the remainder of the MRI scan can be customized to include not only the initial “target,” the lumbar spine, but also areas of incidental abnormality.

[0160] When performing an MR scan, such as on the lumbar spine, a reconnaissance scan or locator scan (e.g., a T1-weighted low-resolution scan; three orthogonal planes) is initially acquired and used to plan the geometry of the diagnostic images that should be acquired.

[0161] Reconnaissance scans can reveal incidental findings (up to 20% on routine MRI of the lumbar spine), and depending on their location, they may not be visible on diagnostic MR images. For example, a kidney or adrenal mass will often be invisible on diagnostic MR images because only a small portion of the kidney is covered. Similarly, an aortic aneurysm may not be visible on diagnostic MR images due to presaturation bands. In both of these cases, the findings may (and often) be included in the reconnaissance images. Some of these findings are subsequently observed at the time of interpretation; unfortunately, others may go undetected. If observed, such patients may be invited for an additional scanning session.

[0162] In many cases, it would be desirable to avoid such additional sessions. These sessions are inconvenient for all parties. Furthermore, they incur additional costs, partly from the extra scans and interpretations (i.e., technical and professional fees) and partly from disruptions to the workflow of both patients and physicians, and the practice environment (e.g., the imaging center). In the service sector, some might support additional charges; in a value-based world, such additional effort is entirely based on cost and is deducted from the pre-negotiated administrative medical contract.

[0163] The paradigm may offer an alternative to the usual approach, ideally allowing for more timely identification of incidental findings, enabling decision-making related to the findings to be made while the patient is still on the scanner bed. In particular, in cases where a reconnaissance scan reveals an incidental finding, the paradigm may allow for a reduction in the need to call the patient back for further imaging sessions.

[0164] The example also potentially allows for the introduction of some degree of artificial / augmented intelligence or deep learning algorithms to improve the sensitivity and potential specificity of detecting such findings.

[0165] An example may contain one or more of the following characteristics:

[0166] 1. Design an MR scan card that includes: 1) higher contrast and / or spatial resolution, which provides improved sensitivity for identifying incidental findings on reconnaissance scans; and 2) improved spatial coverage, which enhances the chance of including common incidental findings (e.g., kidney, aorta, ovary).

[0167] 2. Detect the category of incidental findings in MR reconnaissance scans (e.g., kidney, aorta, ovary) (using methods such as neural networks or model-based approaches) and determine the potential need for additional MR series, and

[0168] 3. In cases of potential need for additional MR scans, trigger rapid two-way communication between the radiologist and the automatically generated reconnaissance images (e.g., directly in person or via remote / cloud-based means (e.g., remote radiography)) for review of the images while the patient is still on the MR scanner, thus enabling additional scans.

[0169] 4. Notify the MR scanner operator via message whether the patient can be released, whether the decision regarding additional MR series is pending, or whether additional scans should be performed, and

[0170] 5. Automatically initiate additional MR series acquisitions when needed.

[0171] Steps 2 and 3 are performed after the acquisition of the reconnaissance scan during the remainder of the MR scan, so that incidental findings may be detected before the patient leaves the MR suite if additional imaging is acquired (if appropriate). Ideally, steps 2 and 3 can be completed before the patient's previously planned imaging has been completed.

[0172] The following example of a lumbar MRI scan illustrates the different steps in the workflow and the techniques used in each step. As a sample protocol, we assume that the standard MR protocol includes axial T1-weighted slices using pre-saturated bands and geometry.

[0173] Figure 7 Another example of the method is illustrated. The method begins at step 700, where a reconnaissance scan is acquired. Next, in step 702, scan planning is performed using the reconnaissance scan. This could be an automated or manual system, for example. After the reconnaissance scan has been acquired, step 706 is performed in parallel. In step 706, findings are detected in the reconnaissance scan, which is equivalent to detecting anatomical deviations. After performing steps 706 and 702, step 708 is performed. In step 708, it is determined whether an additional scan is needed for evaluation. For example, if the anatomical deviation is located within the range of the scan planned in step 702, it may not be necessary. After performing step 702, step 704 is performed. This is to acquire normal medical images; this is equivalent to acquiring clinical tomographic medical image data. After performing step 708, a remote evaluation of the reconnaissance scan 710 is performed. In step 712, information is provided to the operator. Finally, in step 714, additional images are planned and acquired.

[0174] These steps will be discussed in more detail below:

[0175] 700-Collection and Reconnaissance Scan

[0176] Initially, a localization or locator scan is acquired. For example, a reconnaissance scan is a T1-weighted low-resolution scan with three orthogonal planes. The reconnaissance scan covers an area larger than the lumbar spine and, for example, shows the kidneys and possibly the femoral head. The reconnaissance scan is then used for scan planning and processing to detect extraspinal findings. Detection of incidental findings can be performed on the system that performs the scan planning. Alternatively, the reconnaissance scan is sent to a server or the cloud, which performs the detection of incidental findings.

[0177] A prerequisite for identifying incidental discoveries in reconnaissance scanning is sufficient image quality in terms of contrast, spatial resolution, and spatial coverage. To achieve this, in one embodiment, reconnaissance images are acquired again, but with enhanced pre-scan localization techniques such as camera-based identification of anticipated anatomical locations and technological improvements such as compressed sensing, which allow for accelerated image acquisition. This subsequent time saving can be deployed to increase the number of reconnaissance images acquired during the same time period, or to enhance image contrast and spatial resolution, or some of both. Based on this paradigm, improved acquisition of reconnaissance images is achieved.

[0178] 702 - Perform Scan Planning

[0179] Using reconnaissance scanning defines the acquisition of images that should be captured. For a specific example, this means defining the geometry of the axial slices and the presaturation band.

[0180] If a serendipitous discovery has already been detected (step 706), the system can display the discovery detected during scan planning and provide the option to appropriately expand the scan geometry (e.g., additional axial image slices) to cover the area of ​​the serendipitous discovery.

[0181] 704 - Image Acquisition

[0182] After the scan planning is completed, MR images (standard) are acquired.

[0183] 704 - Discovery during reconnaissance scan

[0184] Using a sufficiently large number of annotated reconnaissance scans as the basis for learning, a neural network (such as U-net) can be trained and used to locate and segment (left or right) kidneys in lateral reconnaissance scans. If a (left or right) kidney is seen within the image, another neural network can be trained and used to classify whether the kidney shows an abnormality and what kind of abnormality it shows. Techniques such as Monte Carlo dropout can be used to derive certainty associated with that finding.

[0185] Alternatively, deformable or active shape models can be used to segment the kidneys during reconnaissance scans. Tumors or other abnormalities can then be identified by analyzing the shape of the kidney or the intensity distribution within the kidney.

[0186] As a result of this processing step, the location of the kidney in the (lateral) reconnaissance scan is known, along with an indication and certainty of the presence of abnormalities. This method, and similar methods, can also be applied to other non-renal-related incidental findings.

[0187] Furthermore, specific imaging protocols (MR series information) are associated with each type of incidental discovery. For example, in the case of an incidental discovery related to the kidney, a stack of axial T1- and T2-weighted images covering the kidney can be proposed as an additional MR series.

[0188] 708 - Assess the need for additional scans

[0189] Based on the type, certainty, and classification (clinical significance) of the findings, determine the need for additional scans and / or remote evaluation of the reconnaissance scans by a radiologist. Within this step, the system may also utilize information regarding the planned imaging geometry (step 702), the location of the detected findings, and the need to image the detected findings (MR sequences).

[0190] Three scenarios can be envisioned in this context:

[0191] - No additional scans & no remote assessment. For example, this option should be selected if no findings of high certainty are detected or if the detected findings are not clinically relevant to a large degree of certainty.

[0192] - Additional scans. For example, this option should be selected if clinically relevant findings have already been detected with high certainty, the imaging protocol is clear, and additional imaging effort is limited (e.g., no additional contrast agent is required).

[0193] - Remote assessment. This option should be selected in other situations.

[0194] For example, the parameters and thresholds associated with the decision can be optimized for cost savings associated with performing an additional scan in a single session, based on the additional costs inferred from the remote assessment of the reconnaissance scan.

[0195] 710 - Remote assessment of reconnaissance scans

[0196] Based on the results of step 708, a request is generated for reading the reconnaissance images and for automatically generated review of such images by a radiologist. In response, the system receives information entered by the radiologist: whether additional MR sequences should be acquired and which MR sequences should be acquired. The system may propose a list of suitable imaging protocols derived from the detected findings.

[0197] 712 - Operator Information

[0198] The system notifies the operator about the status of incidental discovery assessments. In particular, it indicates whether the acquisition has been completed, whether the patient can leave the scanning room, or provides information about any additional scans that should be planned and acquired.

[0199] Although in some cases step 6 is completed before the patient's previously planned imaging has been finished, the system may also indicate whether the response of step 6 is still pending.

[0200] 714 - Planning and acquiring additional images

[0201] In cases where additional MR series are requested, the relevant information is automatically obtained from step 6, and the operator can plan and acquire the requested scans. For example, if an abnormality has already been detected in the kidney, the system requires planning an axial T1- and T2-weighted image stack covering the kidney. The system can indicate the location of suspicious lesions or highlight the kidney to support the location of the axial slice stack. Furthermore, the system can add additional margins above and below the kidney to account for uncertainties in kidney position due to respiratory offset. After planning the additional MR series is complete, images are acquired.

[0202] Although the invention has been described in detail in the accompanying drawings and the foregoing description, such description is to be considered illustrative or exemplary rather than restrictive; the invention is not limited to the disclosed embodiments.

[0203] Those skilled in the art, through studying the accompanying drawings, description, and claims, will be able to understand and implement other variations of the disclosed embodiments in practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the words "a" or "an" do not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. Although specific elements are recited in dissimilar dependent claims, this does not imply that combinations of these elements cannot be advantageously used. Computer programs may be stored and / or distributed on suitable media, such as optical storage media or solid-state media provided with or as part of other hardware, but computer programs may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems. No reference numerals in the claims shall be construed as limiting the scope.

Claims

1. A medical system (100, 300, 400) comprising: a tomographic medical imaging system (302, 402) configured for acquiring medical imaging data from an imaging zone; a memory (110) storing machine executable instructions (120) and medical imaging system control commands (320) configured for controlling the tomographic medical imaging system to acquire tomographic medical scout image data; an anatomy detection module (122), wherein the anatomy detection module is configured for detecting an anatomical deviation in response to input tomographic medical scout image data (124), wherein the anatomy detection module is configured for outputting a localization (126) of the anatomical deviation in the tomographic medical scout image data in case the anatomical deviation is detected; a processor (104) configured for controlling the medical system, wherein execution of the machine executable instructions causes the processor to: acquire the tomographic medical scout image data by controlling the tomographic medical imaging system with the medical imaging system control commands; receive clinical scan planning data (322) in response to acquiring the tomographic medical scout image data, wherein the tomographic medical scout image data describes a first region (310), wherein the clinical scan planning data is configured to modify the medical imaging system control commands to acquire clinical tomographic medical image data describing a second region (312), wherein the second region is within the first region, wherein the clinical tomographic medical image data has a higher resolution than the tomographic medical scout image data; construct clinical control commands by modifying the medical imaging system control commands with the clinical scan planning data; acquire clinical tomographic medical imaging data by controlling the medical imaging system with the clinical control commands; input the tomographic medical scout image data into the anatomy detection module; receive (202) the localization of the anatomical deviation from the anatomy detection module in response to inputting the tomographic medical scout image data into the anatomy detection module; provide (204) a warning signal (128) if the localization is received; receive a casual scan indicator (420) from a physician or health care professional via a user interface in response to providing the warning signal, or receive a casual scan indicator (420) from a selected computing device (600) via a network connection (500) in response to sending the warning signal to the selected computing device, wherein the casual scan indicator provides a discharge object selector or a casual scan selector; provide a discharge object signal after completing acquisition of the clinical tomographic medical imaging data if the casual scan indicator provides the discharge object selector; receive casual scan planning data (422) if the casual scan indicator provides the casual scan selector.

2. The medical system of claim 1, wherein, The tomographic medical imaging system is any one of the following: magnetic resonance imaging system (402), computed tomography system, combined computed tomography and positron emission tomography system, and combined magnetic resonance imaging system and positron emission tomography system.

3. The medical system of claim 1 or 2, wherein, The execution of the machine-executable instructions also enables the processor to: Random control commands (424) are constructed by modifying the medical imaging system control commands using the random scan planning data; and The medical imaging system is controlled by the incidental control commands to acquire incidental tomography medical imaging data.

4. The medical system of the preceding claim 1 or 2, wherein, The incidental scan planning data describes a third region (314), wherein the third region is at least partially within the first region, and wherein the third region does not intersect with the second region at least partially.

5. The medical system of the preceding claim 1 or 2, wherein, The execution of the machine-executable instructions causes the warning signal to be sent to the selected computing device before the acquisition of the clinical computed tomography medical imaging data is completed.

6. The medical system of the previous claim 1 or 2, wherein, The medical system includes the selected computing device, wherein the selected computing device includes a display, and wherein the selected computing device is configured to automatically display the warning signal upon receiving the warning signal.

7. The medical system of the previous claim 1 or 2, wherein, The memory includes a list of permitted computing devices (510), wherein the execution of the machine-executable instructions further enables the processor to: Poll the allowed computing devices based on the current user activity; and The selected computing device is selected from the allowed computing devices by applying predetermined selection criteria to the current user activity.

8. The medical system of claim 7, wherein, The current user activity is an indication of when each of the allowed computing devices was last used and / or the current user activity for each of the allowed computing devices.

9. The medical system of claim 7, wherein, At least one of the permitted computing devices is a smartphone, wherein the predetermined selection criteria for selecting the smartphone are the use of an email app or a leisure time app.

10. The medical system of claim 7, wherein, At least one of the permitted computing devices is a radiology workstation, wherein the predetermined selection criteria for selecting the radiology workstation are the workstation's use for reviewing other medical imaging data.

11. The medical system of the previous claim 1 or 2, wherein, The anatomical detection module includes a segmentation algorithm, wherein the segmentation algorithm is adapted to detect the anatomical deviation.

12. The medical system of the previous claim 1 or 2, wherein, The anatomical detection module includes a neural network, wherein the neural network is configured to output the localization of the anatomical deviation in response to receiving a tomographic medical reconnaissance scan.

13. The medical system of claim 12, wherein, The neural network is a UNet neural network, and / or the trained neural network is trained according to the following method: Receive training data, wherein the training data includes training tomographic medical reconnaissance image data, wherein the training data further includes labels, wherein the labels identify the location of anatomical deviations in the training tomographic medical reconnaissance image data, wherein; and The neural network is trained using labeled training data according to a deep learning algorithm.

14. A computer program product comprising machine executable instructions (120) and an anatomical detection module (122), wherein, The machine-executable instructions are configured to be executed by a processor (104) controlling a medical system (100, 300, 400), wherein the medical system includes a tomographic medical imaging system (302, 402) configured to acquire medical imaging data from an imaging area, wherein the anatomical detection module is configured to detect anatomical deviations in response to input tomographic medical reconnaissance image data (124), wherein the anatomical detection module is configured to output the location (126) of the anatomical deviation in the tomographic medical reconnaissance image data upon detection of the anatomical deviation, wherein the execution of the machine-executable instructions causes the processor to: The tomography medical imaging system is controlled by a medical imaging system control command to acquire tomography medical reconnaissance image data, wherein the medical imaging system control command (320) is configured to control the tomography medical imaging system to acquire tomography medical reconnaissance image data. Clinical scan planning data (322) is received in response to the acquisition of the tomographic medical reconnaissance image data, wherein the tomographic medical reconnaissance image data describes a first region (310), wherein the clinical scan planning data is configured to modify the medical imaging system control command to acquire clinical tomographic medical image data describing a second region (312), wherein the second region is within the first region, wherein the clinical tomographic medical image data has a higher resolution than the tomographic medical reconnaissance image data; Clinical control commands are constructed by modifying the medical imaging system control commands using the clinical scan planning data. Clinical tomography medical imaging data is acquired by controlling the medical imaging system using the clinical control commands. The tomographic medical investigation image data is input into the anatomical detection module; In response to inputting the tomographic medical reconnaissance image data into the anatomical detection module, the localization of the anatomical deviation is received (202) from the anatomical detection module; and If the location is received, a warning signal (204) (128) is provided. In response to providing the warning signal, a random scan indicator (420) is received from a physician or healthcare professional via a user interface, or in response to sending the warning signal to a selected computing device (600), a random scan indicator (420) is received from the selected computing device via a network connection (500), wherein the random scan indicator provides a discharge subject selector or a random scan selector; If the incidental scan indicator provides the discharge subject selector, then a discharge subject signal is provided after the acquisition of the clinical tomographic medical imaging data is completed; If the random scan indicator provides the random scan selector, then the random scan planning data (422) is received.

Images