Anatomical segmentation of tomographic images containing anatomical anomalies

Abstract

A medical system (100, 300, 400, 500) is disclosed herein. Execution of the machine executable instructions (120) causes the computing system (104) to: receive (200) an input tomographic medical image (126) depicting an anatomical anomaly (800), receive (202) a modified tomographic medical image (126) without an anatomical anomaly in response to inputting the input tomographic medical image into an image processing neural network (122), an anatomical segmentation (130) of the modified tomographic medical image is received (204) in response to inputting the modified tomographic medical image into an image segmentation module (128), where the anatomical segmentation divides the modified tomographic medical image into a plurality of anatomical regions, and the anatomical segmentation is provided (206) as a segmentation of the input tomographic medical image.

Description

Technical Field

[0001] The present invention relates to tomographic medical imaging technology, and in particular to segmentation of tomographic medical images. Background Art

[0002] Various tomographic medical imaging techniques, such as magnetic resonance imaging (MRI), computed tomography, positron emission tomography, and single photon emission tomography, enable detailed visualization of the anatomy of a subject.After a tomographic medical image is acquired, it is typically segmented or divided into multiple anatomical regions.

[0003] International patent application publication WO2022057312A1 discloses a medical image processing method, apparatus, device and storage medium. The method comprises: extracting a mask of tissue abnormality from multiple tissue abnormality images with marking information; randomly selecting one or more masks, and generating a new tissue abnormality image on the selected one or more masks by using a Gaussian function; collecting the coordinate values ​​of the abnormal tissue prediction area in the normal tissue sample image; and superimposing the new tissue abnormality image on the image corresponding to the abnormal tissue prediction area according to the coordinate values, so as to obtain a simulated tissue abnormality image. It discloses the simulation of tissue abnormality images, and can control the form, size, grayscale distribution and generation position of the lesion.

[0004] US patent application US2020 / 364864 discloses a GAN-based method for mapping irregular medical images to standard medical images. In the standard medical image, the abnormal area in the input image includes synthetic anatomical data. Summary of the invention

[0005] The invention provides a medical system, a computer program and a method in the independent claims. Embodiments are given in the dependent claims.

[0006] The difficulty in segmenting tomographic medical images is that if there are any anatomical abnormalities (such as tumors), they may cause the image segmentation module to fail. The image segmentation module can be implemented using one or more different techniques, such as neural networks, shape deformable models, or anatomical atlas registration. If there are anatomical abnormalities, these image segmentation modules may output incorrect anatomical segmentations. An embodiment may provide an improved means for segmenting tomographic medical images with anatomical abnormalities. First, an input tomographic medical image with anatomical abnormalities is input into an image processing neural network, which has been trained to output a modified tomographic medical image similar to the input tomographic medical image, but the anatomical abnormalities have been removed. The modified tomographic medical image is essentially a simulated tomographic medical image. The image segmentation module is then used to segment the modified tomographic medical image to provide anatomical segmentation. The anatomical segmentation of the modified tomographic medical image is then provided as a segmentation of the input tomographic medical image.

[0007] In one aspect, the present invention provides a medical system comprising a memory storing machine executable instructions and also storing an image processing neural network. The image processing neural network is a neural network that receives an image and also outputs an image. The image processing neural network is configured to output a modified tomographic medical image describing a selected anatomical region of an object in response to receiving an input tomographic medical image describing the selected anatomical region. The image processing neural network is also configured to output a modified tomographic medical image such that anatomical abnormalities depicted in the input tomographic medical image are removed. For example, a tumor or other anatomical abnormality may be depicted in the input tomographic medical image. This is then removed by the image processing neural network and a new image is constructed without the anatomical abnormality depicted therein.

[0008] The present invention relates to an image processing neural network that returns a modified tomographic medical image from an input tomographic medical image in which an anatomical abnormality is depicted. From the modified tomographic image, the anatomical abnormality is removed by the image processing neural network. An anatomical segmentation of the modified tomographic image (i.e., without the anatomical abnormality) into a plurality of anatomical regions is received from a segmentation module. The segmentation is then applied to the input tomographic image (with the anatomical abnormality).

[0009] The medical system also includes a computing system. Execution of the machine executable instructions causes the computing system to receive an input tomographic medical image. Execution of the machine executable instructions further causes the computing system to receive a modified tomographic medical image in response to inputting the input tomographic medical image into the image processing neural network. Execution of the machine executable instructions further causes the computing system to receive an anatomical segmentation of the modified tomographic medical image in response to inputting the modified tomographic medical image into the image segmentation module.

[0010] The anatomical segmentation divides the modified tomographic medical image into a plurality of anatomical regions. That is, the image segmentation module is configured to divide the modified tomographic medical image into a plurality of anatomical regions. The execution of the machine executable instructions also causes the computing system to provide the anatomical segmentation as a segmentation of the input tomographic medical image. This may be beneficial because a conventional image segmentation module may fail if there are anatomical abnormalities. For example, if it is a formal image segmentation module for plastic surgery, the presence of anatomical abnormalities such as tumors, growths, or abnormal anatomical structures may cause the segmentation module to fail and output an incorrect anatomical segmentation. Using the anatomical segmentation of the modified tomographic medical image may provide a better segmentation of the input tomographic medical image.

[0011] The image segmentation module can be implemented in various ways. For example, it can be done using a neural network such as U-net or a similar encoder-decoder network (such as a V-net neural network). The image segmentation module can be a deformable shape model. In other examples, the image segmentation can be a registration with an anatomical atlas.

[0012] In different examples, the tomographic medical image can be, for example, a positron emission tomography (PET) image, a single photon emission computed tomography (SPECT), a computed tomography (CT) image, a magnetic resonance (MR) image, which can be a combination of positron emission tomography and magnetic resonance images, or a combined computed tomography and magnetic resonance image, or other variations.

[0013] The image processing neural network can be constructed in different ways. For example, the image processing neural network can be a recurrent GAN neural network or a variational autoencoder.

[0014] If the image processing neural network is a recurrent GAN, it can be trained using standard recurrent GAN methods based on unpaired training images with and without abnormalities / pathologies. A suitable approach is described in the arXive paper 1810.10850v2 by Sun et al., April 8, 2019, “An Adversarial learning approach to medical image synthesis forlesion detection”.

[0015] If the image processing neural network is a variational autoencoder, the training data includes both anatomically normal images and pathological images, both of which are mapped to their latent space representations. In the latent space of the autoencoder, the average position of anatomically normal and anatomically abnormal images can be determined and a difference vector calculated. When a tomographic medical image has an anatomical abnormality, its representation in the latent space can be shifted by the difference vector to remove the anatomical abnormality.

[0016] In another embodiment, execution of the machine executable instructions further causes the computing system to provide an image mask identifying the location of anatomical abnormalities in the input magnetic resonance image by comparing the input tomographic medical image with the modified tomographic medical image. For example, the images may be subtracted from each other. The difference between the input tomographic medical image and the modified tomographic medical image may then be thresholded, and this may provide a suitable image mask.

[0017] In another embodiment, execution of the machine executable instructions further causes the computing system to provide an image mask identifying the location of anatomical abnormalities in an input tomographic medical image by receiving the image mask from the image processing neural network. The image processing neural network is further configured to output the image mask. During training, the location of the anatomical abnormalities may be marked in the ground-truth image. Marking the location of the anatomical abnormalities in the ground-truth image may provide a basis for training the image processing neural network to also output the image mask.

[0018] In another embodiment, execution of the machine executable instructions further causes the computing system to determine a geometric metric describing the anatomical abnormality in each of the plurality of anatomical regions using the image mask and the anatomical segmentation. The geometric metric may, for example, be a quantitative intrusion metric describing the fractional volume of the anatomical abnormality in each of the plurality of anatomical regions. In other examples, the geometric metric may describe the distance that the anatomical abnormality intrudes into each of the plurality of anatomical regions. In yet other examples, the geometric metric may describe the surface area of ​​the anatomical abnormality in each of the plurality of anatomical regions.

[0019] This embodiment may be beneficial because the image mask provides information about the size and location of the anatomical abnormality, and the anatomical segmentation provides information about what the anatomical region would look like without the anatomical abnormality. This provides a means to quantitatively measure the effects of the anatomical abnormality on various anatomical regions of the subject. Such measurements may not be possible using conventional segmentation techniques.

[0020] In another embodiment, execution of the machine executable instructions further causes the computing system to render a composite image that superimposes the anatomical segmentation on the input tomographic medical image. This may be beneficial because it may provide a means of visualizing anatomical regions that have been affected by anatomical abnormalities. It may also provide a means of verifying or judging the validity of the anatomical segmentation.

[0021] In another embodiment, execution of the machine executable instructions further causes the computing system to emphasize areas of the anatomical segmentation within the image mask and in the composite image. Areas within the image mask may be less reliable because these areas are areas containing anatomical abnormalities. This can be a means of drawing attention to areas of the anatomical segmentation that may be less accurate or incorrect. They can also be provided to the user as a warning about the accuracy of the segmentation within the image mask or, for example, within a tumor. The emphasis of these areas can be considered a warning signal.

[0022] In another embodiment, the execution of the machine executable instructions further causes the computing system to receive a second segmentation of the input tomographic medical image in response to inputting the input tomographic medical image into the segmentation module. The execution of the machine executable instructions further causes the computing system to identify at least one warning zone of the anatomical segmentation by determining an area of ​​the anatomical segmentation that differs from the second segmentation by more than a predetermined threshold. For example, a warning zone may be provided if the distance between the anatomical segmentation and the second segmentation at a particular point changes by more than a threshold distance. An identification of the at least one warning zone may then be provided as a warning signal. The execution of the machine executable instructions further causes the computing system to mark the warning zone on the composite image. For example, this may result in the segmentation having a different appearance or a different color.

[0023] In another embodiment, the memory further stores an anatomical abnormality segmentation module configured to output an abnormality segmentation constrained to an image portion of the input tomographic medical image. The execution of the machine executable instructions further causes the computing system to determine an input portion of the input tomographic medical image based on the location of the anatomical abnormality defined in the image mask. The execution of the machine executable instructions further causes the computing system to receive the abnormality segmentation by applying the abnormality segmentation module to the input portion of the tomographic medical image. The abnormality segmentation module can be a segmentation module designed to specifically segment anatomical abnormalities or specific types of anatomical abnormalities. For example, the abnormality segmentation module can be designed to segment specific types of tumors or other pathologies.

[0024] In another embodiment, the anatomical abnormality segmentation module is any one of: a neural network such as a deep learning trained neural network, threshold segmentation, fuzzy theory based image segmentation, region based image segmentation, and edge based image segmentation.

[0025] In another embodiment, execution of the machine executable instructions further causes the computing system to modify the anatomical segmentation using the anomaly segmentation. For example, the anomaly segmentation can be concatenated or combined with the anatomical segmentation. Or, for example, a region of the anatomical segmentation outside of the anomaly segmentation can be used generally and then simply combined with the anomaly segmentation. This can provide a better definition of the anatomical region and a better definition of the region that more accurately defines the anatomical anomaly.

[0026] In another embodiment, execution of the machine executable instructions further causes the computing system to receive configuration data configured to configure the anatomical abnormality segmentation module from a user interface. Execution of the machine executable instructions further causes the computing system to modify the operation of the anatomical abnormality segmentation module before applying the anatomical abnormality segmentation module to the input portion of the tomographic medical image. For example, the user interface can be used to define things such as seed points, gray value intervals, selection of segmentation module types or modes. This can be beneficial because it can provide a more accurate segmentation of anatomical abnormalities.

[0027] In another embodiment, the image processing neural network is a recurrent GAN neural network.

[0028] In another embodiment, the image processing neural network is a variational autoencoder. In another embodiment, the medical system further comprises a tomographic medical imaging system. The memory further comprises imaging system control commands configured to control the medical imaging system to acquire medical imaging data describing a selected anatomical region of the object. Execution of the machine executable instructions further causes the computing system to acquire medical imaging data by controlling the tomographic medical imaging system using the imaging system control commands. Execution of the machine executable instructions further causes the computing system to reconstruct an input tomographic medical image from the medical imaging data.

[0029] In another embodiment, the memory further comprises a radiation therapy planning module configured to output radiation therapy system control commands in response to receiving the location of one or more target zones, the anatomical segmentation, and the location of one or more protected zones within the selected anatomical region where irradiation is preferably minimized, the radiation therapy system control commands being configured to control the radiation therapy system to irradiate the one or more target zones in the selected anatomical region. Execution of the machine executable instructions further causes the computing system to output radiation therapy system control commands in response to receiving the location of one or more target zones, the anatomical segmentation, and preferably the location of one or more protected zones. This embodiment may be beneficial because the use of anatomical segmentation may provide more accurate and safe radiation therapy.

[0030] In some instances, the location of the anatomical abnormality may be the same as the one or more target regions.

[0031] In another embodiment, the medical system further comprises a radiotherapy system. The execution of the machine executable instructions further causes the computing system to irradiate the one or more target areas by controlling the radiotherapy system using the radiotherapy control commands. This embodiment may be beneficial because it may provide more accurate irradiation of the one or more target areas and provide a higher degree of safety for the subject.

[0032] In another embodiment, the radiation therapy system is a LINAC system.

[0033] In another embodiment, the radiation therapy system is a Gamma Knife.

[0034] In another embodiment, the radiation therapy system is an X-ray radiation therapy system.

[0035] In another aspect, the invention provides a computer program comprising machine executable instructions and an image processing neural network. Both the machine executable instructions and the image processing neural network may be executable by a computing system. The image processing neural network is configured to output a modified tomographic medical image describing a selected anatomical region of an object in response to receiving an input tomographic medical image describing the selected anatomical region of the object. The image processing neural network is further configured to output the modified tomographic medical image such that anatomical abnormalities depicted in the input tomographic medical image are removed. Execution of the machine executable instructions causes the computing system to receive the input tomographic medical image.

[0036] Execution of the machine executable instructions further causes the computing system to receive a modified tomographic medical image in response to inputting the input tomographic medical image into the image processing neural network. Execution of the machine executable instructions further causes the computing system to receive an anatomical segmentation of the modified tomographic medical image in response to inputting the modified tomographic medical image into the image segmentation module. The anatomical segmentation divides the modified tomographic medical image into a plurality of anatomical regions. Execution of the machine executable instructions further causes the computing system to provide the anatomical segmentation as a segmentation of the input tomographic medical image.

[0037] In another aspect, the present invention provides a medical imaging method. The method includes receiving an input tomographic medical image. The input tomographic medical image describes a selected anatomical region of an object and picks out anatomical abnormalities. The method also includes receiving a modified tomographic medical image in response to inputting the input tomographic medical image into an image processing neural network. The image processing neural network is configured to output a modified tomographic medical image describing the selected anatomical region in response to receiving the input tomographic medical image describing the selected anatomical region of the object. The image processing neural network is also configured to output a modified tomographic medical image such that anatomical abnormalities depicted in the input tomographic medical image are removed. The method also includes receiving an anatomical segmentation of the modified tomographic medical image in response to inputting the modified tomographic medical image into an image segmentation module. The anatomical segmentation divides the modified tomographic medical image into a plurality of anatomical regions. The method also includes providing the anatomical segmentation as a segmentation of the input tomographic medical image.

[0038] It should be understood that one or more of the aforementioned embodiments of the present invention may be combined as long as the combined embodiments are not mutually exclusive.

[0039] As will be appreciated by those skilled in the art, aspects of the present invention may be implemented as an apparatus, method, or computer program product. Accordingly, aspects of the present invention may take the form of a fully hardware embodiment, a fully software embodiment (including firmware, resident software, microcode, etc.), or a combination of software and hardware aspects (all of which may be generally referred to herein as "circuits," "modules," or "systems"). In addition, aspects of the present invention may take the form of a computer program product implemented in one or more computer-readable media having computer executable code implemented thereon.

[0040] Any combination of one or more computer-readable media may be utilized. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. As used herein, "computer-readable storage medium" encompasses any tangible storage medium that can store instructions that can be executed by a processor of a computing device or a computing system. 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.

[0041] In some embodiments, the computer-readable storage medium can also store data that can be accessed by the computing system of the computing device. Examples of computer-readable storage media include, but are not limited to, floppy disks, magnetic hard disk drives, solid-state hard disks, flash memory, USB thumb drives, random access memory (RAM), read-only memory (ROM), optical disks, magneto-optical disks, and register files of computing systems. Examples of optical disks include compact disks (CDs) and digital versatile disks (DVDs), such as CD-ROMs, CD-RWs, CD-Rs, DVD-ROMs, DVD-RWs, or DVD-R disks. The term computer-readable storage medium also refers to various types of recording media that can be accessed 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 can be sent using any suitable medium, and any suitable medium includes, but is not limited to, wireless, wired, optical fiber cables, RF, etc., or any suitable combination of the foregoing.

[0042] A computer readable signal medium may include a propagated data signal having computer executable code implemented therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including but not limited to electromagnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and is capable of conveying, propagating, or transmitting a program used by or in conjunction with an instruction execution system, apparatus, or device.

[0043] "Computer memory" or "memory" is an example of a computer-readable storage medium. Computer memory is any memory that is directly accessible by a computing system. "Computer storage" or "storage" is another example of a computer-readable storage medium. A computer storage is any non-volatile computer-readable storage medium. In some embodiments, a computer storage may also be computer memory, or vice versa.

[0044] As used herein, "computing system" encompasses an electronic component capable of running a program or machine executable instructions or computer executable code. References to computing systems including examples of "computing system" should be interpreted as possibly including more than one computing system or processing core. The computing system may be, for example, a multi-core processor. A computing system may also refer to a collection of computing systems within a single computer system or distributed across multiple computer systems. The term computing system should also be interpreted as possibly referring to a collection or network of computing devices that each include a processor or computing system. Machine executable code or instructions may be run by multiple computing systems or processors that may be within the same computing device or may even be distributed across multiple computing devices.

[0045] Machine executable instructions or computer executable code may include instructions or programs that cause a processor or other computing system to perform aspects of the present invention. Computer executable code for performing operations for various aspects of the present invention may be written in any combination of one or more programming languages ​​and compiled into machine executable instructions, and the one or more programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, C++, etc. and conventional procedural programming languages ​​such as "C" programming language or similar programming languages. In some instances, the computer executable code may take the form of a high-level language or take a precompiled form and be used in conjunction with a decoder that generates machine executable instructions at work. In other instances, machine executable instructions or computer executable code may take the form of programming for programmable logic gate arrays.

[0046] The computer executable code may run entirely on the user's computer, partially on the user's computer (as a stand-alone 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 through 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., through the Internet using an Internet service provider).

[0047] Aspects of the present invention are described with reference to the flowchart, diagram and / or block diagram of the method, device (system) and computer program product according to an embodiment of the present invention. It should be understood that, when applicable, each frame or part of the frame of the flowchart, diagram and / or block diagram can be implemented by a computer program instruction in the form of a computer executable code. It should also be understood that, when mutually non-exclusive, the combination of frames in different flowcharts, diagrams and / or block diagrams can be combined. These computer program instructions can be provided to the computing system of a general-purpose computer, a special-purpose computer or other programmable data processing device that produces a machine, so that the instruction running via the computing system of a computer or other programmable data processing device creates a unit for implementing the function / action specified in a flowchart and / or one or more block diagram frames.

[0048] These machine-executable instructions or computer program instructions may also be stored in a computer-readable medium, which can direct a computer, other programmable data processing apparatus, or other device to work in a specific manner, so that the instructions stored in the computer-readable medium produce an article of manufacture including instructions for implementing the functions / actions specified in the flowchart and / or one or more block diagram blocks.

[0049] The machine-executable instructions or computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other device, thereby producing a computer-implemented process, so that the instructions running on the computer or other programmable apparatus provide a process for the functions / actions specified in the flowchart and / or one or more block diagram blocks.

[0050] As used herein, "user interface" is an interface that allows a user or operator to interact with a computer or computer system. "User interface" may also be referred to as a "human-machine interface device". A user interface may provide information or data to an operator and / or receive information or data from an operator. A user interface may enable the input from an operator to be received by a computer and may provide output to a user from a computer. In other words, the user interface may allow an operator to control or manipulate a computer, and the interface may allow a computer to indicate the effect of the control or manipulation of an operator. The display of data or information on a display or graphical user interface is an example of providing information to an operator. The reception of data by a keyboard, mouse, tracking ball, touch pad, pointing stick, graphic input board, joystick, game controller, webcam, earphone, pedal, wired gloves, remote controller, and accelerometer are all examples of user interface components that implement the reception of information or data from an operator.

[0051] As used herein, "hardware interface" encompasses an interface that enables a computing system of a computer system to interact with and / or control an external computing device and / or apparatus. A hardware interface may allow a computing system to send a control signal or instruction to an external computing device and / or apparatus. A hardware interface may also enable a computing system to exchange data with an external computing device and / or apparatus. Examples of hardware interfaces include, but are not limited to, a universal serial bus, an IEEE 1394 port, a parallel port, an IEEE 1284 port, a serial port, an RS-232 port, an IEEE-488 port, a Bluetooth connection, a wireless LAN connection, a TCP / IP connection, an Ethernet connection, a control voltage interface, a MIDI interface, an analog input interface, and a digital input interface.

[0052] As used herein, a "display" or "display device" encompasses an output device or user interface suitable for displaying images or data. A display may output visual, audio, and / or tactile data. Examples of displays include, but are not limited to, computer monitors, television screens, touch screens, tactile electronic displays, Braille screens, cathode ray tubes (CRTs), memory tubes, bi-stable displays, electronic paper, vectorscopes, 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 displays (OLEDs), projectors, and head mounted displays.

[0053] Medical imaging data is defined herein as the recorded measurements made by a tomographic medical imaging system describing an object. The medical imaging data can be reconstructed into a medical image. A tomographic medical image is defined herein as a reconstructed two-dimensional or three-dimensional visualization of the anatomical data contained within the medical imaging data. Such visualization can be performed using a computer.

[0054] K-space data is defined herein as the measurements of radio frequency signals emitted by atomic spins recorded using the antenna of a magnetic resonance apparatus during a magnetic resonance imaging scan. Magnetic resonance data is an example of tomographic medical image data.

[0055] A magnetic resonance imaging (MRI) image or MR image is defined herein as a reconstructed two-dimensional or three-dimensional visualization of anatomical data contained within magnetic resonance imaging data. Such visualization can be performed using a computer. A magnetic resonance image is an example of a tomographic medical image. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Preferred embodiments of the present invention will hereinafter be described, by way of example only, and with reference to the accompanying drawings, in which:

[0057] Figure 1 An example of a medical system is illustrated;

[0058] Figure 2 The diagram shows the use of Figure 1 A flowchart of a method of a medical system;

[0059] Figure 3 Further examples of medical systems are illustrated;

[0060] Figure 4 The diagram shows the use of Figure 3 A flowchart of a method of a medical system;

[0061] Figure 5 Further examples of medical systems are illustrated;

[0062] Figure 6 Further examples of medical systems are illustrated;

[0063] Figure 7 The diagram shows the use of Figure 6 A flowchart of a method of a medical system;

[0064] Figure 8 illustrates examples of an input tomographic medical image and a modified tomographic medical image; and

[0065] Fig. 9 An example of a model-based segmentation module is illustrated.

[0066] Reference numerals list

[0067] 100 Medical Systems

[0068] 102 Computer

[0069] 104 Computing System

[0070] 106 Hardware Interface

[0071] 108 User Interface

[0072] 110 Memory

[0073] 120 machine executable instructions

[0074] 122 Image Processing Neural Network

[0075] 124 Input tomographic medical images

[0076] 126 Modified Tomographic Medical Images

[0077] 128 Image Segmentation Module

[0078] 130 Anatomical segmentation

[0079] 200 receives an input tomographic medical image.

[0080] 202 Receiving the modified tomographic medical image in response to inputting the input tomographic medical image into the image processing neural network.

[0081] 204 Receive an anatomical segmentation of the modified tomographic medical image in response to inputting the modified tomographic medical image into an image segmentation module.

[0082] 206 provides the anatomical segmentation as a segmentation of the input tomographic medical image.

[0083] 300 Medical Systems

[0084] 302 Tomography Medical Imaging System

[0085] 304 Imaging Area

[0086] 306 objects

[0087] 308 support

[0088] 320 Imaging System Control Commands

[0089] 320' pulse sequence command

[0090] 322 Medical Imaging Data

[0091] 322'k space data

[0092] 324 Image Mask

[0093] 326 Geometric Measurement

[0094] 328 composite images

[0095] 330 Emphasis Area

[0096] 400 acquires the medical imaging data by controlling the tomographic medical imaging system using the imaging system control command.

[0097] 402 reconstructs the input tomographic medical image based on the medical imaging data.

[0098] 404 providing an image mask, the image mask identifying the location of the anatomical abnormality in the input tomographic medical image;

[0099] 406 Determine a geometric metric describing the anatomical abnormality in at least one anatomical region of the plurality of anatomical regions using the image mask and the anatomical segmentation.

[0100] 408 Rendering a composite image superimposing the anatomical segmentation on the input tomographic medical image;

[0101] 410 Emphasizing the anatomically segmented region within the image mask in the composite image.

[0102] 500 Medical Systems

[0103] 502 Magnetic Resonance Imaging System

[0104] 504 magnet

[0105] 506 magnet bore

[0106] 508 Field of View

[0107] 510 magnetic field gradient coil

[0108] 512 Magnetic Field Gradient Coil Power Supply

[0109] 514 RF Coil

[0110] 516 transceiver

[0111] 600 Medical Systems

[0112] 602 Radiation Therapy System

[0113] 604 rack

[0114] 606 Radiotherapy Source

[0115] 608 Collimator

[0116] 610 Cryostat

[0117] 612 superconducting coil

[0118] 614 Rotating axis

[0119] 616 Radiation Beam

[0120] 618 Target Area

[0121] 620 Radiation Therapy Planning Module

[0122] 622 Radiation therapy system control commands

[0123] 700 outputs radiation therapy system control commands in response to receiving the location of one or more target volumes and the anatomical segmentation.

[0124] 702 irradiates the one or more target zones by controlling the radiotherapy system using the radiotherapy system control commands.

[0125] 800 Anatomical Abnormalities

[0126] 802 Difference Image

[0127] 804 is used to generate high contrast areas of the image mask DETAILED DESCRIPTION

[0128] Like numbered elements in these figures are either equivalent elements or perform the same function. Elements that have been discussed previously will not necessarily be discussed in subsequent figures if the function is equivalent.

[0129] Figure 1 An example of a medical system 100 is illustrated. The medical system 100 is shown to include a computer 102. The computer 102 may represent one or more computers at one or more locations. For example, the computer 102 may be a virtual machine available within a cloud-based system.

[0130] Computer 102 is shown to include a computing system 104. Computing system 104 can represent one or more computing systems or processing cores located at one or more locations. Computing system 104 is shown to communicate with an optional hardware interface 106. If present, hardware interface 106 can be used to control other components, such as a medical imaging system or even a magnetic resonance imaging system. Computing system 104 is shown to further communicate with a user interface 108. If present, an operator can use user interface 108 to control and interact with medical system 100. Computing system 104 is also shown to communicate with memory 110. Memory 110 is intended to represent various types of memory accessible to computing system 104. For example, memory 110 can be a non-transitory storage medium. In other examples, memory 110 can be ordinary computer RAM.

[0131] The memory 110 is shown as containing machine executable instructions 120. The machine executable instructions 120 enable the computing system 104 to perform various data manipulation, image manipulation, and computing tasks. In some examples, the machine executable instructions 120 may also enable control of the medical imaging system via the hardware 106. The memory 110 is also shown as containing an image processing neural network 124. The memory 110 is also shown as containing an input tomographic medical image 124. The memory 110 is also shown as containing a modified tomographic medical image 126. The image processing neural network 122 is configured to receive the input tomographic medical image 124 and, in response, output a modified tomographic medical image 126. The input tomographic medical image 124 may have anatomical abnormalities, and this may be removed so that it is no longer present in the modified tomographic medical image 126.

[0132] The memory 110 is also shown as containing an image segmentation module 128 for segmenting the modified tomographic medical image 126. The memory 110 is also shown as containing an anatomical segmentation 130 received from the image segmentation module 128 in response to the input modified tomographic medical image 126. The anatomical segmentation 130 may be used as a segmentation of the input tomographic medical image 124. This may have the advantage that the anatomical segmentation 130 is not affected by the presence of anatomical abnormalities. For example, this may enable the input tomographic medical image 124 to be accurately divided into different anatomical regions despite the possible presence of anatomical abnormalities, such as the presence of a tumor.

[0133] Figure 2 The diagram shows the operation Figure 1Flowchart of a method of a medical system 100 of the present invention. First, in step 200, an input tomographic medical image 124 is received. For example, this can be received by retrieving it from the memory 110, it can be received via a network connection, or it can be received by acquiring or reconstructing the input tomographic medical image 124. Next, in step 202, a modified tomographic medical image 126 is received in response to inputting the input tomographic medical image 124 into an image processing neural network. The image processing neural network is configured to output a modified tomographic medical image 126 such that anatomical abnormalities depicted in the input tomographic medical image 124 are removed. The method also includes providing an anatomical segmentation 130 as a segmentation of the input tomographic medical image 124 in step 206. In different examples, providing the anatomical segmentation can take different forms. In one instance, the anatomical segmentation can be overlaid on the input tomographic medical image 124. In other instances, it can be associated with the input tomographic medical image 124, for example the input tomographic medical image 124 can be stored in a so-called DICOM file. In this case, the anatomical segmentation 130 may be appended to the DICOM file.

[0134] Figure 3 Another example of a medical system 300 is shown. The system 300 is similar to Figure 1 1, except that it additionally includes a tomographic medical imaging system 302. The tomographic medical imaging system 302 is intended to represent a variety of system types. For example, it can be a magnetic resonance imaging system, a positron emission tomography system, a computed tomography system, a single photon emission tomography system, or a combined modality, such as a combined CT and MR system or a combined CT and positron emission tomography system.

[0135] The tomographic medical imaging system 302 has a subject support 308 that supports a subject 306 within an imaging region 304 .

[0136] The memory 110 is also shown as containing imaging system control commands 320 for controlling the operation and functionality of the tomographic medical imaging system 302. The memory 110 is also shown as containing medical imaging data 322 that has been collected and describes the imaging area 304. The medical imaging data 322 is collected or measured by controlling the tomographic medical imaging system 302 with the imaging system control commands 320.

[0137] The memory 110 is also shown as containing an image mask 324 that has been determined by comparing the input tomographic medical image 124 and the modified tomographic medical image 126. For example, one can be subtracted from the other, and the difference can be thresholded. This can identify the location of the anatomical abnormality. In other examples, the image processing neural network 122 can be designed or trained to also output the image mask 324. The memory 110 is also shown as containing a geometric metric 326 that uses the image mask 324 and the anatomical segmentation 130 to describe the anatomical abnormality in one or more of the multiple anatomical regions. For example, this can be a measure of the fractional volume of the anatomical abnormality within some or all of the multiple anatomical regions for other things (such as invasion distance or surface area).

[0138] The memory is also shown as containing a composite image 328, which is a combination of the anatomical segmentation 130 and the input tomographic medical image 124. The memory 110 is also shown as containing emphasized regions 330 that have been determined for the composite image 328. These may be regions of the anatomical segmentation 130 that are within the location of the image mask 324. They may be emphasized, for example, by changing their appearance, color, or other optical properties, so that the operator knows that the anatomical segmentation 130 is within the anatomical abnormality.

[0139] Figure 4 The diagram shows the operation Figure 3 Flow chart of a method of a medical system 300 of the present invention. First, in step 400, the tomographic medical imaging system 302 is controlled by using the imaging system control command 320 to acquire medical imaging data 322. Next, in step 402, the input tomographic medical image 124 is reconstructed based on the medical imaging data 322. Next, the method repeats as shown in FIG. Figure 2 Steps 200, 202, 204 and 206 are shown. After performing step 206, the method proceeds to step 404. In step 404, an image mask 324 is provided. The image mask 324 provides the location of the anatomical abnormality in the input tomographic medical image 124. This can be done, for example, by subtracting the input tomographic medical image 124 and the modified tomographic medical image 126. Next, in step 406, a geometric metric 326 describing the anatomical abnormality in at least one anatomical region of the plurality of anatomical regions is determined using the image mask 324 and the anatomical segmentation 130. Then, in step 408, a composite image 328 is drawn. The composite image 328 superimposes the anatomical segmentation 130 on the input tomographic medical image 124. Finally, in step 410, the region 330 of the anatomical segmentation 130 within the image mask 324 is emphasized in the composite image 328.

[0140] Figure 5Another example of a medical system 500 is shown. The medical system 500 is similar to Figure 3 , except that in this case the tomographic medical imaging system 302 is a magnetic resonance imaging system 502 .

[0141] The magnetic resonance imaging system 502 comprises a magnet 504. The magnet 504 is a superconducting cylindrical magnet having a bore 506 passing through it. It is also possible to use different types of magnets; for example, split cylindrical magnets and so-called open magnets can also be used. 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 isoplane of the magnet, such a magnet can be used, for example, in conjunction with charged particle beam therapy. An open magnet has two magnet parts, one above the other, with a space between them large enough to receive an object: the arrangement of the two partial areas is similar to that of a Helmholtz coil. Open magnets are popular because the object is less restricted. Inside the cryostat of the cylindrical magnet, there is a collection of superconducting coils.

[0142] An imaging zone 304 exists within a bore 506 of a cylindrical magnet 504, wherein the magnetic field is sufficiently strong and uniform to perform magnetic resonance imaging. A field of view 508 is shown within the imaging zone 304. The acquired magnetic resonance data is typically acquired with respect to the field of view 508. An object 306 is shown supported by an object support 308, such that at least a portion of the object 306 is within the imaging zone 304 and the field of view 508.

[0143] There is also a set of magnetic field gradient coils 510 in the bore 506 of the magnet, which is used to acquire preliminary magnetic resonance data to spatially encode magnetic spins in the imaging zone 304 of the magnet 504. The magnetic field gradient coils 510 are connected to a magnetic field gradient coil power supply 512. The magnetic field gradient coils 510 are intended to be representative. Typically, the magnetic field gradient coils 510 include three separate 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 510 is controlled as a function of time and can be ramped or pulsed.

[0144] Adjacent to the imaging zone 304 is a radio frequency coil 514 for manipulating the orientation of magnetic spins within the imaging zone 304 and for receiving radio transmissions from spins also within the imaging zone 304. The radio frequency antenna may contain multiple coil elements. The radio frequency antenna may also be referred to as a channel or antenna. The radio frequency coil 514 is connected to a radio frequency transceiver 516. The radio frequency coil 514 and the radio frequency transceiver 516 may be replaced by separate transmit and receive coils and separate transmitters and receivers. It should be understood that the radio frequency coil 514 and the radio frequency transceiver 516 are representative. The radio frequency coil 514 is also intended to represent a dedicated transmit antenna and a dedicated receive antenna. Similarly, the transceiver 516 may also represent a separate transmitter and receiver. The radio frequency coil 514 may also have multiple receive / transmit elements, and the radio frequency transceiver 516 may have multiple receive / transmit channels. For example, if a parallel imaging technique such as SENSE is performed, the radio frequency coil 514 will have multiple coil elements.

[0145] The transceiver 516 and the gradient controller 512 are shown connected to the hardware interface 506 of the computer system 502 .

[0146] In this example, the imaging system control command 320 is a pulse sequence command 320'. The pulse sequence command 320' is a command or data that can be converted into a command for controlling the magnetic resonance imaging system 502 to acquire k-space data. In this example 110, the medical imaging data is k-space data 322'.

[0147] Figure 6 The diagram shows Figure 5 6 is another example of a medical system 600 that is similar to the medical system 500 depicted in , except that it additionally includes a radiation therapy system 602. In this example, the magnetic resonance imaging system 502 is used to guide the radiation therapy system 602. This is intended to be exemplary. For example, the magnetic resonance imaging system 502 may be replaced with a computed tomography system.

[0148] The radiation therapy system 602 includes a gantry 604 and a radiation therapy source 606. The gantry 604 is used to rotate the radiation therapy source 606 about a gantry rotation axis or rotation axis 614. A collimator 608 is adjacent to the radiation therapy source 606.

[0149] The magnet 504 shown in this embodiment is a standard cylindrical superconducting magnet. The magnet 504 has a cryostat 610 having superconducting coils 612 therein. A split magnet could alternatively be used.

[0150] There is a target area 618 within the subject 306. In this example, the gantry rotation axis 614 is coaxial with the cylindrical axis of the magnet 504. The radiation source 606 is aimed at the rotation axis 614 so that the radiation source has a target volume around the rotation axis 614.

[0151] The object support 308 has been positioned so that the target area 618 is located on the gantry rotation axis 614. The radiation source 606 is shown as generating a radiation beam 616 that passes through the collimator 608 and passes through the target area 618. As the radiation source 606 rotates around the axis 614, the target area 618 will always be aimed at by the radiation beam 616. The radiation beam 616 passes through the cryostat 610 of the magnet 604. The magnetic field gradient coil can have a gap that divides the magnetic field gradient coil into two parts. If present, the gap reduces the attenuation of the radiation beam 616 by the magnetic field gradient coil 510. In some embodiments, the radio frequency coil 514 can also have a gap or be separated to reduce the attenuation of the radiation beam 616.

[0152] The memory 110 is also shown as containing a radiation therapy planning module 620. The radiation therapy planning module 620 is configured to output radiation therapy system control commands configured to control the radiation therapy system 602 in response to receiving the location of the one or more target zones 618, the anatomical segmentation 130, and optionally the location of one or more protected zones within the selected anatomical region to minimize irradiation. The memory is also shown as containing radiation therapy system control commands 622 generated using the radiation therapy planning module 620.

[0153] Figure 7 Graphical operation Figure 6 First, Figure 4 Steps 400, 402, 200, 202, 204 and 206 are performed as shown. Next, the following operations are performed in the following steps:

[0154] 700 Outputting radiation therapy system control commands in response to receiving the location of one or more target volumes, the anatomical segmentation, and preferably the location of one or more protected regions

[0155] 702 irradiating one or more target areas by controlling the radiotherapy system using the radiotherapy system control commands

[0156] The performance of anatomical image segmentation algorithms often suffers from abnormal contrast or the presence of anatomical abnormalities such as tumors, fractures or other types of lesions, since they are usually trained on non-pathological contrast.

[0157] An example may provide a system capable of improving the segmentation of pathology scans by utilizing artificial intelligence. Its main element is a component that estimates the normal-looking correspondence of abnormal images, for which the anatomical segmentation algorithm is expected to work more reliably. This segmentation result is then mapped to the original abnormal image and visualized together with the reliability information obtained from the mapping.

[0158] Many segmentation methods that learn geometric properties and / or gray value characteristics from data - e.g., some model-based segmentation or other machine and deep learning based methods - are trained and thus optimized for healthy controls and may fail in case of abnormal contrast caused by lesions or pathologies. For example, segmentation of subcortical brain structures may fail in case of brain tumors or massive white matter lesions. The reason is that such pathological contrasts are very diverse in size, location and appearance, making it difficult to fully cover their expected variability in training. However, since the typically expected gray values ​​may be significantly altered due to such pathologies, they may significantly hinder correct segmentation.

[0159] The example can solve the above problem by using artificial intelligence to artificially "remove" any pathological contrast, abnormality or lesion in the test image to be segmented. Therefore, the abnormal test image is transformed into an image with normal contrast together with a mask indicating which image areas contain abnormalities and have therefore been modified. The segmentation algorithm is then applied to the transformed image with normal contrast, where accurate and robust segmentation results are expected to be produced. The result is then transferred to the original abnormal image. All parts of the segmentation result in the area of ​​the image mask (i.e., in the area containing the abnormality) are marked (e.g., displayed in a more transparent manner) to indicate that they are unreliable in the presence of abnormalities. In addition, the segmentation results can also be applied to the original abnormal test image; comparing the segmentation of the abnormal image and the transformed normal-looking image, the two segments are significantly different (even outside the image mask) The area can be marked as "unreliable".

[0160] Examples may contain one or more of the following characteristics:

[0161] Fully automatic statistical segmentation algorithm (image segmentation module 128) (e.g., model-based segmentation, voxel-based segmentation, etc.),

[0162] Automated algorithms (image processing neural networks 122) for automatically removing the contrast of abnormalities, lesions and pathologies, e.g. based on artificial intelligence / generative adversarial networks, transforming abnormal images into normal-looking images without pathological contrast, abnormalities and lesions, and (binary) image masks indicating which image areas contain abnormalities and have therefore been modified,

[0163] a graphical display of the segmentation results, in which the parts of the segmentation corresponding to the masked image regions are visually modified to indicate that they are not reliable in the presence of anomalies,

[0164] a comparator which compares the segmentation result of the original abnormal image with that of the transformed healthy-looking image, the result of which is fed into a graphical display of the segmentation results; and also indicates areas of significant difference of the two segmentation results (even outside the mask),

[0165] A user interface and additional segmentation methods specifically tailored to segment abnormal tissue in a marked volume of interest, wherein the volume of interest is set to match the region of the image mask, and the user interface is used to manually select a suitable segmentation method and manually set additional boundary conditions (e.g., seed points, gray value intervals, etc.).

[0166] The abnormal image (input tomographic medical image 124) is transformed into an image with normal-looking contrast (modified tomographic medical image 124) by manually removing abnormalities, pathological contrast, and lesion contrast using an automated algorithm from artificial intelligence.

[0167] Figure 8 Several images are shown. Image 124 is an example of an input tomographic medical image that is a magnetic resonance image, and an anatomical abnormality 700, in this case a tumor, is clearly present. Image 126 is an example of a modified tomographic medical image 126 that has been generated by inputting the input tomographic medical image 124 into the image processing neural network 122. The tumor 700 has been removed from the image. Image 702 is a difference image between images 124 and 126. In this case, there is a high contrast area 704 indicating the location of the anatomical abnormality 700 or tumor. An image mask 324 can be constructed by thresholding image 702. This will identify the area marked as 704 in the mask.

[0168] After the modified tomographic medical image 126 has been generated, a statistical segmentation algorithm (image segmentation module 128) (eg, model-based segmentation) is then applied to the transformed normal-looking image, see below. Fig. 9 Due to the absence of pathological contrast, abnormalities and lesions, the segmentation results are expected to be more accurate and robust.

[0169] Fig. 9 Several views of a modified tomographic medical image 126 are illustrated, in which an anatomical segmentation 130 has been fitted. It shows a model-based segmentation of subcortical structures and cortical tissue classes (grey matter, white matter, cerebrospinal fluid) in a (normal-looking) MR volume.

[0170] Next, the generated segmentation (anatomical segmentation 130) is transferred back to the original abnormal image (input tomographic medical image 124). The generated image mask defines the areas where the original image differs from the transformed image; those parts of the segmentation result that are located in the image mask are displayed in a modified manner (e.g., with greater transparency) to indicate that they are unreliable due to the presence of the abnormality.

[0171] Optionally, the segmentation results (anatomical segmentation 130) can also be applied to the original abnormal image (input tomographic medical image 126). Comparing the segmentation of the abnormal image and the normal-looking image, all areas with significant deviations (even outside the image mask) define unreliable segmentations and can be visually indicated (again using transparency or any other suitable visual indicator).

[0172] Furthermore, if a dedicated segmentation algorithm for a specific type of abnormality is available (which could be a simple region growing algorithm in a spatially constrained area for segmenting the lesion), the second segmentation step can be triggered by a corresponding user interface, involving manual selection of a suitable segmentation algorithm and manual definition of additional constraints, such as defining a volume of interest or seed points.

[0173] While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive; the invention is not limited to the disclosed embodiments.

[0174] Those skilled in the art can understand and implement other variations of the disclosed embodiments when practicing the claimed invention by studying the drawings, the disclosure and the claims. In the claims, the word "comprising" does not exclude other elements or steps, and the words "one" or "an" do not exclude multiple. A single processor or other unit can satisfy the functions of several items recorded in the claims. Although specific measures are recorded in mutually different dependent claims, this does not indicate that a combination of these measures cannot be used to advantage. The computer program can be stored and / or distributed on appropriate media, such as optical storage media or solid-state media provided with or as part of other hardware, but the computer program can also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems. Any figure mark in the claims should not be interpreted as limiting the scope.

Claims

1. A medical system (100, 300, 500, 600), comprising: a memory (110) storing machine executable instructions (120) and an image processing neural network (122), wherein the image processing neural network is configured to output a modified tomographic medical image (126) depicting a selected anatomical region of a subject in response to receiving an input tomographic medical image (124) depicting the selected anatomical region of the subject, wherein the image processing neural network is further configured to output the modified tomographic medical image such that an anatomical abnormality (800) depicted in the input tomographic medical image is removed; A computing system (104), wherein execution of the machine executable instructions causes the computing system to: receiving (200) said input tomographic medical image; receiving (202) the modified tomographic medical image in response to inputting the input tomographic medical image into the image processing neural network; and receiving (204) an anatomical segmentation (130) of the modified tomographic medical image in response to inputting the modified tomographic medical image into an image segmentation module (128), wherein the anatomical segmentation divides the modified tomographic medical image into a plurality of anatomical regions; and The anatomical segmentation is provided (206) as a segmentation of the input tomographic medical image.

2. The medical system according to claim 1, wherein: Execution of the machine-executable instructions further causes the computing system to provide (404) an image mask that identifies the location of the anatomical abnormality in the input tomographic medical image by any of the following operations: comparing the input tomographic medical image with the modified tomographic medical image (802); and The image mask is received from the image processing neural network, wherein the image processing neural network is further configured to output the image mask.

3. The medical system according to claim 2, wherein: Execution of the machine-executable instructions further causes the computing system to determine (406) a geometric metric (326) using the image mask and the anatomical segmentation, the geometric metric describing the anatomical abnormality in at least one anatomical region of the plurality of anatomical regions.

4. The medical system according to claim 2 or 3, wherein: Execution of the machine-executable instructions further causes the computing system to render (408) a composite image (328) superimposing the anatomical segmentation on the input tomographic medical image.

5. The medical system according to claim 4, wherein: Execution of the machine-executable instructions further causes the computing system to emphasize (410) in the composite image the region (330) of the anatomical segmentation that is within the image mask.

6. The medical system according to claim 4 or 5, wherein: Execution of the machine-executable instructions further causes the computing system to: receiving a second segmentation of the input tomographic medical image in response to inputting the input tomographic medical image into the image segmentation module; identifying at least one warning zone of the anatomical segmentation by determining an area of ​​the anatomical segmentation that differs from the second segmentation by more than a predetermined threshold; and The warning area is marked on the composite image.

7. The medical system according to any one of claims 2 to 6, wherein: The memory further stores an anatomical anomaly segmentation module configured to output an anomaly segmentation constrained to an image portion of the input tomographic medical image, wherein execution of the machine-executable instructions further causes the computing system to: determining said input portion of said input tomographic medical image according to said location of said anatomical abnormality defined in said image mask; The anomaly segmentation is received by applying the anatomical anomaly segmentation module to the input portion of the tomographic medical image.

8. The medical system according to claim 7, wherein: Execution of the machine-executable instructions further causes the computing system to modify the anatomical segmentation using the anomaly segmentation.

9. The medical system according to claim 7 or 8, wherein: Execution of the machine-executable instructions further causes the computing system to: receiving, from a user interface, configuration data configured to configure the anatomical anomaly segmentation module; Operation of the anatomical anomaly segmentation module is modified prior to applying the anatomical anomaly segmentation module to the input portion of the tomographic medical image.

10. The medical system according to any one of the preceding claims, wherein: The image processing neural network is any one of the following: a recurrent GAN neural network, a variational autoencoder, and a U-Net.

11. The medical system according to any one of the preceding claims, wherein: The medical system further comprises a tomographic medical imaging system (302, 502), wherein the memory further comprises imaging system control commands (320, 320') configured to control the tomographic medical imaging system to acquire medical imaging data (322, 322'), the medical imaging data describing the selected anatomical region of the subject, wherein execution of the machine-executable instructions further causes the computing system to: acquiring (400) the medical imaging data by controlling the tomographic medical imaging system using the imaging system control commands; and The input tomographic medical image is reconstructed (402) from the medical imaging data.

12. The medical system according to any one of the preceding claims, wherein: The memory also includes a radiotherapy planning module (620), which is configured to output a radiotherapy system control command (622) in response to receiving the position of one or more target areas (618) in the selected anatomical region, the anatomical segmentation, and preferably the position of one or more protected areas in the selected anatomical region to minimize irradiation, and the radiotherapy system control command is configured to control the radiotherapy system (602) to irradiate the one or more target areas; wherein the execution of the machine-executable instructions also causes the computing system to output (700) the radiotherapy system control command in response to receiving the position of the one or more target areas, the anatomical segmentation, and preferably the position of the one or more protected areas.

13. The medical system according to claim 12, wherein: The medical system also includes the radiation therapy system, wherein execution of the machine-executable instructions further causes the computing system to irradiate (702) the one or more target zones by controlling the radiation therapy system using the radiation therapy system control commands.

14. A computer program comprising machine executable instructions (120) and an image processing neural network (122), wherein: The image processing neural network is configured to, in response to receiving an input tomographic medical image (124) depicting a selected anatomical region of an object, output a modified tomographic medical image (126) depicting the selected anatomical region, wherein the image processing neural network is further configured to output the modified tomographic medical image such that anatomical abnormalities depicted in the input tomographic medical image are removed (800), wherein execution of the machine executable instructions causes the computing system to: receiving (200) said input tomographic medical image; receiving (202) the modified tomographic medical image in response to inputting the input tomographic medical image into the image processing neural network; receiving (204) an anatomical segmentation (130) of the modified tomographic medical image in response to inputting the modified tomographic medical image into an image segmentation module (128), wherein the anatomical segmentation divides the modified tomographic medical image into a plurality of anatomical regions; and The anatomical segmentation is provided (206) as a segmentation of the input tomographic medical image.

15. A medical imaging method, wherein: The method comprises: Receiving (200) an input tomographic medical image (124); receiving (202) a modified tomographic medical image (126) in response to inputting the input tomographic medical image into an image processing neural network (122), wherein the image processing neural network is configured to output the modified tomographic medical image depicting a selected anatomical region of a subject in response to receiving the input tomographic medical image depicting the selected anatomical region, wherein the image processing neural network is further configured to output the modified tomographic medical image such that anatomical abnormalities depicted in the input tomographic medical image are removed (800); receiving (204) an anatomical segmentation (130) of the modified tomographic medical image in response to inputting the modified tomographic medical image into an image segmentation module (128), wherein the anatomical segmentation divides the modified tomographic medical image into a plurality of anatomical regions; and The anatomical segmentation is provided (206) as a segmentation of the input tomographic medical image.

Images