EP4128261A1 - Erzeugen von radiologischen aufnahmen - Google Patents
Erzeugen von radiologischen aufnahmenInfo
- Publication number
- EP4128261A1 EP4128261A1 EP21713686.0A EP21713686A EP4128261A1 EP 4128261 A1 EP4128261 A1 EP 4128261A1 EP 21713686 A EP21713686 A EP 21713686A EP 4128261 A1 EP4128261 A1 EP 4128261A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- radiological
- recordings
- artificial
- contrast
- radiological recordings
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G06T7/0014—Biomedical image inspection using an image reference approach
- G06T7/0016—Biomedical image inspection using an image reference approach involving temporal comparison
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R33/00—Arrangements or instruments for measuring magnetic variables
- G01R33/20—Arrangements or instruments for measuring magnetic variables involving magnetic resonance
- G01R33/44—Arrangements or instruments for measuring magnetic variables involving magnetic resonance using nuclear magnetic resonance [NMR]
- G01R33/48—NMR imaging systems
- G01R33/54—Signal processing systems, e.g. using pulse sequences ; Generation or control of pulse sequences; Operator console
- G01R33/56—Image enhancement or correction, e.g. subtraction or averaging techniques, e.g. improvement of signal-to-noise ratio and resolution
- G01R33/5601—Image enhancement or correction, e.g. subtraction or averaging techniques, e.g. improvement of signal-to-noise ratio and resolution involving use of a contrast agent for contrast manipulation, e.g. a paramagnetic, super-paramagnetic, ferromagnetic or hyperpolarised contrast agent
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R33/00—Arrangements or instruments for measuring magnetic variables
- G01R33/20—Arrangements or instruments for measuring magnetic variables involving magnetic resonance
- G01R33/44—Arrangements or instruments for measuring magnetic variables involving magnetic resonance using nuclear magnetic resonance [NMR]
- G01R33/48—NMR imaging systems
- G01R33/54—Signal processing systems, e.g. using pulse sequences ; Generation or control of pulse sequences; Operator console
- G01R33/56—Image enhancement or correction, e.g. subtraction or averaging techniques, e.g. improvement of signal-to-noise ratio and resolution
- G01R33/5608—Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—Two-dimensional [2D] image generation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/41—Medical
Definitions
- the present invention relates to the generation of radiological recordings of an examination area of an examination subject. On the basis of such measured radiological recordings of an examination area, which show blood vessels in the examination area with contrast enhancement decreasing over time, the present invention generates artificial radiological recordings of the examination area which show blood vessels with constant contrast enhancement.
- Radiology is a medical specialty that deals with imaging for diagnostic and therapeutic purposes.
- CT computed tomography
- MRT magnetic resonance imaging
- sonography sonography
- contrast media substances that facilitate the representation or delimitation of certain structures in an examination subject. These substances are called contrast media.
- iodine-containing solutions are mostly used as contrast media.
- MRI magnetic resonance imaging
- superparamagnetic substances e.g. iron oxide nanoparticles, superparamagnetic iron-platinum particles (SIPPs)
- paramagnetic substances e.g. gadolinium chelates, manganese chelates
- contrast agents can be found in the literature (see e.g. ASL Jascinth et al .: Contrast Agents in computed tomography: A Review, Journal of Applied Dental and Medical Sciences, 2016, Vol. 2, Issue 2, 143-149; H. Lusic et al .: X-ray-Computed Tomography Contrast Agents, Chem. Rev. 2013, 113, 3, 1641-1666; https://www.radiology.wisc.edu/wp-content/uploads/2017/10/ contrast- agents-tutorial.pdf, MR Nough et al .: Radiographie and magnetic resonances contrast agents: Essentials and tips for safe practices, World J Radiol.
- contrast media can be roughly divided into the following categories: extracellular, mixed extra- / intracellular (often referred to simply as intracellular contrast media) and blood pool contrast media.
- the extracellular MRT contrast media include, for example, the gadolinium chelates gadobutrol (Gadovist ® ), gadoteridol (Prohance ® ), gadoteric acid (Dotarem ® ), gadopentetic acid (Magnevist ® ) and gadodiamide (Omnican ® ).
- gadolinium chelates gadobutrol (Gadovist ® ), gadoteridol (Prohance ® ), gadoteric acid (Dotarem ® ), gadopentetic acid (Magnevist ® ) and gadodiamide (Omnican ® ).
- Gadovist ® gadobutrol
- Prohance ® gadoteridol
- Dotarem ® gadoteric acid
- Magnnevist ® gadopentetic acid
- Omnican ® gadodiamide
- Mixed extra- / intracellular contrast media are absorbed in the toes by tissues to a certain extent and then excreted again.
- Mixed extra- / intracellular MRI contrast media based on gadoxetic acid are characterized, for example, by the fact that they are partially specifically absorbed by the toes of the liver, the hepatocytes, accumulate in the functional tissue (parenchyma) and the contrasts in healthy liver tissue increase before they are then excreted in the faeces via bile.
- Examples of such contrast media based on gadoxetic acid are described in US Pat. No. 6,039,931A; they are commercially available, for example under the brand names Primovist ® and Eovist ®.
- Gadobenate Dimeglumine (Multihance ® ) is another MRI contrast agent with a lower absorption into the hepatocytes.
- Blood pool (contrast) agents also referred to as intravascular contrast media
- Gadofosveset is, for example, an intravascular MRI contrast medium based on gadolinium. It was used as the trisodium salt monohydrate form (Ablavar ® ). It binds to serum albumin, which means that the contrast agent remains in the blood for a long time (half-life in the blood around 17 hours).
- Ablavar ® was withdrawn from the market in 2017. Another contrast agent approved as a blood pool contrast agent for magnetic resonance imaging is not commercially available. Likewise, there is no contrast agent on the market that has been approved as a blood pool contrast agent for computed tomography.
- the present invention addresses this problem.
- the present invention provides means with which radiological recordings can be simulated on the basis of a blood pool contrast agent.
- a first object of the present invention is a computer-implemented method comprising the steps
- the measured radiological recordings showing an examination area of an examination subject at different, successive times after application of a contrast agent, the contrast agent leading to a contrast enhancement of blood vessels in the examination area, the contrast enhancement of the blood vessels in the measured radiological recordings decrease with increasing time,
- Another object of the present invention is a computer system comprising a receiving unit, a control and computing unit and an output unit, the control and computing unit being configured to cause the receiving unit to receive a sequence of measured radiological recordings, the measured radiological recordings forming an examination area of an examination subject at different, consecutive times after an application of a contrast agent, the contrast agent contributing to a contrast enhancement of blood vessels in the The examination area leads, the contrast enhancement of the blood vessels in the measured radiological recordings decreasing with increasing time, the control and computing unit being configured to use the measured radiological recordings to calculate a sequence of artificial radiological recordings, the contrast enhancement of the blood vessels in the artificial radiological Recordings are retained over time, the control and computing unit being configured to cause the output unit to output the artificial radiological recordings.
- Another object of the present invention is a computer program product comprising a computer program that can be loaded into a main memory of a computer and there causes the computer to carry out the following steps:
- the measured radiological recordings showing an examination area of an examination subject at different, successive times after application of a contrast agent, the contrast agent leading to a contrast enhancement of blood vessels in the examination area, the contrast enhancement of the blood vessels in the measured radiological recordings decrease with increasing time,
- Another object of the present invention is the use of a contrast agent in a radiological examination method, the radiological examination method comprising the following steps:
- Another object of the present invention is a contrast agent for use in a radiological examination method, the radiological examination method comprising the following steps:
- Another object of the present invention is a kit comprising a contrast agent and the computer program product according to the invention.
- the present invention generates a sequence of artificial radiological recordings of an examination area of an examination subject, the artificial radiological recordings showing the examination area after application of a blood pool contrast agent, although no blood pool contrast agent has been applied.
- the present invention uses a sequence of measured radiological recordings of an examination area to simulate a sequence of artificial radiological recordings of the examination area after application of an intravascular contrast agent.
- the present invention on the basis of a sequence of radiological recordings which show an examination area of an examination subject, the present invention generates a sequence of artificial radiological recordings which show the examination area as it would appear if a blood pool contrast agent had been administered.
- a radiologist is thus able to generate a sequence of radiological recordings of an examination area of an examination subject, which look as if a blood pool contrast agent had been administered to the examination subject without the radiologist having administered such an intravascular contrast agent.
- an intravascular contrast agent is synonymous with the term “artificial radiological image that shows an examination area as it looks / would look after application of an intravascular contrast agent”.
- Exposure is used in this description for both measured and artificially generated (calculated) radiological representations of an examination area.
- the “object to be examined” is usually a living being, preferably a mammal, very particularly preferably a human.
- the “examination area”, also called the field of view (FOV), represents in particular a volume that is mapped in the radiological recordings.
- the examination area is typically determined by a radiologist, for example on a localizer. Of course he can The examination area can alternatively or additionally also be determined automatically, for example on the basis of a selected protocol.
- the examination area can be, for example, the liver or part of the liver, the lungs or part of the lungs, the heart or part of the heart, the aorta or part of the aorta, abdominal blood vessels, leg and pelvic blood vessels, the esophagus or part the esophagus, the stomach or part of the stomach, the small intestine or part of the small intestine, the large intestine or part of the large intestine, the abdomen or part of the abdomen, the pancreas or part of the pancreas and / or another part of the subject be or include this.
- the radiological examination is preferably an MRT examination. Accordingly, the at least one (measured) radiological recording that is recorded by the examination area is preferably an MRT recording, and the at least one artificially generated radiological recording is also an MRT recording.
- the radiological examination is a CT examination; accordingly, the at least one (measured) radiological recording that is recorded by the examination area is, in this embodiment, a CT recording, and the at least one artificially generated radiological recording is also a CT recording.
- Measured / metrologically generated radiological recordings and artificially generated radiological recordings can be present as two-dimensional image recordings which show a section plane through the examination subject.
- the radiological recordings can be present as a stack of two-dimensional image recordings, with each individual image record of the stack showing a different cutting plane.
- the radiological recordings can be available as three-dimensional recordings (3D recordings).
- 3D recordings three-dimensional recordings
- the radiological recordings are usually available as digital image files.
- digital means that the radiological images can be processed by a machine, usually a computer system.
- Processcessing is understood to mean the known procedures for electronic data processing (EDP).
- Digital image files can be in a variety of formats.
- Digital image files can be encoded as raster graphics, for example.
- Raster graphics consist of a raster-shaped arrangement of so-called image points (pixels) or volume elements (voxels), each of which is assigned a color or a gray value.
- the main characteristics of a 2D raster graphic are therefore the image size (width and height measured in pixels, colloquially also called image resolution) and the color depth.
- a color is usually assigned to a pixel in a digital image file.
- the color coding used for a pixel is defined, among other things, by the color space and the color depth. The simplest case is a binary image in which a pixel saves a black and white value.
- each pixel In an image whose color is defined via the so-called RGB color space (RGB stands for the basic colors red, green and blue), each pixel consists of three subpixels, one subpixel for the color red, one subpixel for the color green and one Subpixels for the color blue.
- the color of an image point results from the superposition (additive mixing) of the color values of the subpixels.
- the color value of a subpixel can, for example, be divided into 256 color nuances, the tone values and usually range from 0 to 255.
- the color shade "0" of each color channel is the darkest. If all three channels have the tone value 0, the corresponding pixel appears black; if all three channels have the tone value 255, the corresponding pixel appears white.
- digital image files (radiological recordings) are subjected to certain operations.
- the operations mainly concern the pixels or the tonal values of the individual pixels.
- digital image formats and color codings There are a variety of possible digital image formats and color codings.
- the present images are grayscale raster graphics with a specific number of image points, with each image point being assigned a tone value which indicates the gray value of the image.
- this assumption should in no way be understood as limiting. It is clear to the person skilled in the art of image processing how he can transfer the teaching of this description to image files which are present in other image formats and / or in which the color values are coded differently.
- a sequence of measured radiological recordings is received.
- These measured radiological recordings can be TI-weighted, T2-weighted and / or diffusion-weighted representations and / or recordings that have been generated with the aid of another recording sequence.
- a sequence of measured radiological recordings comprises at least two radiological recordings.
- sequence means chronological sequence, i.e. several (at least two) radiological recordings are generated using measurement technology, which show the examination area at successive points in time.
- a point in time is assigned to each recording or a point in time can be assigned to each recording. This point in time is usually the point in time at which the recording was generated (absolute time).
- the radiological recordings are assigned arbitrary points in time (e.g. relative points in time).
- a recording can be assigned the time of the start of the recording or the time of the completion of the recording.
- a radiological recording can be classified in relation to another radiological recording; Based on the point in time of a radiological recording, it can be established whether the moment shown in the radiological recording occurred before or after a moment shown in another radiological recording.
- the radiological recordings are preferably arranged in time in a sequence such that recordings which show an earlier state of the examination area are arranged in the sequence before such recordings which show a later state of the examination region.
- the time span between two recordings directly following one another in a sequence is preferably the same for all pairs of recordings directly following one another in the sequence, i.e. the recordings were preferably generated at a constant recording rate.
- the measured radiological recordings of the sequence preferably show an examination area of an examination subject at different, successive points in time after an application of a contrast agent, the contrast agent leading to a contrast enhancement of blood vessels in the measured radiological recordings of the examination area, the contrast enhancement of the blood vessels in the measured radiological ones Recordings decrease with increasing time.
- a sequence can also comprise a native radiological image (native image); Such a native image shows the examination area without administration of a contrast agent.
- the applied contrast agent can be an extracellular and / or a mixed extra- / intracellular contrast agent. In a preferred embodiment, it is an extracellular contrast medium. In a further preferred embodiment, it is a mixed extra- / intracellular contrast medium.
- a contrast agent is administered to the examination subject (in a further step).
- the contrast agent can be an MRT contrast agent or a CT contrast agent. It is preferably an extracellular MRT contrast agent such as gadobutrol, gadoteridol, gadoteric acid, gadopentetic acid and / or gadodiamide.
- Other extracellular MRI contrast agents are described in the literature (see e.g. Yu.Dong Xiao et al .: MRI contrast agents: Classification and application (Review), International Journal of Molecular Medicine 38: 1326 (2016)).
- the contrast agent is a mixed extra- / intracellular MRI contrast agent such as Gd-EOB-DTPA (Primovist ®), Mn-DPDP (mangafodipir), Gd-BOPTA (Gadobenate-Dimelglumin) and / or Gd-DTPA mesoporphyrin (gadophrin) act.
- Gd-EOB-DTPA Primarymovist ®
- Mn-DPDP mangafodipir
- Gd-BOPTA Gadobenate-Dimelglumin
- Gdophrin Gdophrin
- Other mixed extra- / intracellular MRI contrast agents are described in the literature (see e.g. Yu.Dong Xiao et al .: MRI contrast agents: Classification and application (Review), International Journal of Molecular Medicine 38: 1326 (2016)).
- the contrast agent is preferably introduced into a blood vessel of the examination subject, for example into an arm vein. From there it moves with the blood along the bloodstream.
- the "blood circulation” is the path that the blood travels in the body of humans and most animals. It is the blood flow system that is formed by the heart and a network of blood vessels (cardiovascular system, blood vessel system).
- the arteries transport blood under high pressure and at high flow rates. It is through them that the blood from the heart reaches the various tissues.
- the arterioles branch off from the arteries; they serve as control valves and have strong muscular walls that can narrow the vessels (vasoconstriction) or widen them (vasodilation). They branch further to the capillaries, which carry out the exchange of fluids, nutrients, electrolytes, hormones and other substances between blood and tissue and are equipped with a thin vessel wall that is permeable to low-molecular substances.
- the capillaries In some organs (liver, spleen) the capillaries are widened and the endothelium becomes discontinuous, then one speaks of sinusoids.
- Venules only have a thin vessel wall; they collect the blood from the capillaries to return it to the veins that carry it from the periphery back to the heart.
- An extracellular contrast medium circulates in the bloodstream for a period of time that depends on the examination subject, the contrast medium and the amount administered, while it is continuously removed from the bloodstream by the kidneys.
- At least one radiological recording of the blood vessel system or a part thereof is recorded.
- At least one radiological image of that part of the blood vessel system which is located in the examination area is preferably acquired.
- Several radiological recordings can be acquired which show different phases of the distribution of the contrast agent in the blood vessel system or a part thereof (for example flooding phase, arterial phase, venous phase and / or the like).
- the acquisition of several recordings allows a later differentiation of blood vessel types.
- the measured radiological recordings show the blood vessel system or a part thereof, in particular the part which is located in the examination area, with a contrast-enhanced contrast to the surrounding tissue.
- at least a first radiological recording shows arteries with a high contrast (arterial phase)
- at least a second radiological recording shows veins with a high contrast (venous phase).
- Artificial radiological recordings are generated on the basis of the measured radiological recordings.
- the artificial radiological recordings preferably show the same examination area as the measured radiological recordings. If a large number of measured radiological recordings were recorded from the examination area at different times after the application of the contrast agent, the later radiological recordings in particular show blood vessels with an increasingly decreasing contrast to the surrounding tissue, since the contrast agent is gradually separated from the blood vessels.
- the artificial radiological images show the blood vessels with a consistently high contrast to the surrounding tissue.
- a predictive model is used.
- the prediction model can have been trained on the basis of reference data to compensate for a contrast enhancement of blood vessels that decreases over time.
- the prediction model can have been trained on the basis of reference data to generate a sequence of artificial radiological images that cover the examination area after application of an extracellular or a mixed extra / intracellular contrast agent on the basis of a sequence of measured radiological recordings that show an examination area of an examination subject after application of an extracellular or a mixed extra / intracellular contrast agent Show blood pool contrast agent.
- the prediction model can have been trained on the basis of reference data to generate a sequence of artificial radiological recordings for a sequence of measured radiological recordings that show blood vessels in an examination area at different times after application of a contrast agent, the blood vessels in the examination area are contrast-enhanced and with an over show a constant contrast to the surrounding tissue over time.
- the reference data that are used to train and validate such a prediction model usually include measured radiological recordings of the examination area after the application of an extracellular or mixed extra / intracellular contrast agent.
- the reference data can also include radiological recordings of the examination area after the application of a blood pool contrast agent.
- Such reference data can be determined in a clinical study, for example.
- Ferumoxytol for example, can be used as an intravascular contrast medium in such a clinical study.
- Ferumoxytol is a colloidal iron-carbohydrate complex that is approved for the parenteral treatment of iron deficiency in chronic kidney disease when oral therapy is not feasible. Ferumoxytol will administered as an intravenous injection.
- Ferumoxytol is available as a solution for intravenous injection marketed under the brand name Rienso ® or Ferahme®.
- the iron-carbohydrate complex shows superparamagnetic properties and can therefore be used (off-label) for contrast enhancement in MRI examinations (see e.g. LP Smits et al .: Evaluation of ultrasmall superparamagnetic iron-oxide (USPIO) enhanced MRI with ferumoxytol to quantify arterial wall inflammation, Atherosclerosis 2017, 263: 211-218).
- USPIO ultrasmall superparamagnetic iron-oxide
- Another object of the present invention is therefore the use of ferumoxytol or a comparable other blood pool contrast agent, which is approved for intravenous injection, as a blood pool contrast agent for generating a training data set for predicting artificial radiological recordings after application of a blood pool contrast agent of measured radiological recordings after application of an extracellular or a mixed extra- / intra-zehular contrast medium.
- ferumoxytol or a comparable other blood pool contrast agent which is approved for intravenous injection
- a blood pool contrast agent for generating a training data set for predicting artificial radiological recordings after application of a blood pool contrast agent of measured radiological recordings after application of an extracellular or a mixed extra- / intra-zehular contrast medium.
- existing (existing) of radiographic images after application is conceivable was an intravascular contrast agent as training data to be used, yet commercially available, for example from the time when Ablavar ®.
- the reference data can, however, also include artificially generated radiological recordings in which the time-decreasing contrast enhancement of the blood vessels in measured radiological recordings has subsequently been compensated for by image processing methods.
- image processing methods are known in the art (see, eg: MA Joshi: Digital Image Processing - An Algorithmic Approach, PHI Learning Private Limited, 2nd Edition 2018, ISBN: 978-93- 81472-58-7).
- the prediction mode can be trained in supervised learning to learn a relationship between the measured radiological recordings and the radiological recordings after application of the blood pool contrast agent or the recordings processed by means of image processing methods. This learned relationship can then be used to calculate artificial radiological recordings for new measured radiological recordings, the artificial radiological recordings showing the examination area as it would look after application of a blood pool contrast agent, with an extracular one for the measured radiological recordings or a mixed extra- / intracellular contrast agent has been administered: blood vessels in the examination area show an increased contrast that remains constant over time compared to the surrounding tissue.
- the prediction mode is thus trained to compensate for the time-decreasing contrast agent enhancement of blood vessels in measured radiological images.
- the prediction mode can be, for example, or comprise an artificial neural network.
- Such an artificial neural network comprises at least three layers of processing elements: a first layer with input neurons (nodes), an N-th layer with at least one output neuron (node) and N-2 inner layers, where N is a natural number and greater than 2 .
- the input neurons are used to receive (digital) measured radiological recordings as input values. There is usually an input neuron for each pixel or voxei in a digital radiological image. Additional input neurons for additional input values (e.g. information on the examination area, on the examination subject and / or on conditions that prevailed when the radiological recordings were made) can be present.
- the output neurons serve to output the artificial radiological recordings (to be available).
- the processing elements of the layers between the input neurons and the output neurons are connected to one another in a predetermined pattern with predetermined connection weights.
- the artificial neural network is preferably a so-called convolutional neural network (CNN for short).
- a convolutional neural network is able to process input data in the form of a matrix. This enables digital radiological recordings displayed as a matrix (e.g. width x height x color channels) to be used as input data.
- a normal neural network e.g. in the form of a multi-layer perceptron (MLP), on the other hand, requires a vector as input, i.e. in order to use a radiological image as input, the pixels or voxels of the radiological image would have to be rolled out in a long chain one after the other.
- normal neural networks are e.g. not able to recognize objects in a radiological image regardless of the position of the object in the image. The same object at a different position in the shot would have a completely different input vector.
- a CNN essentially consists of filters (convolutional layer) and aggregation layers (pooling layer), which are alternately repeated, and at the end of one or more layers of "normal" completely connected neurons (dense / fully connected layer).
- Recurrent neural networks are a family of artificial neural networks that contain feedback connections between layers. RNNs allow sequential data to be modeled by sharing parameter data across different parts of the neural network.
- the architecture for an RNN contains cycles. The cycles represent the influence of a current value of a variable on its own value at some future point in time, since at least some of the output data from the RNN is used as feedback for processing subsequent inputs in a sequence.
- the training of the neural network can be carried out, for example, by means of a backpropagation method.
- the most reliable possible mapping of given input vectors to given output vectors is sought for the network.
- the quality of the image is described by an error function.
- the aim is to minimize the error function ⁇
- the teaching of a artificial neural network takes place in the backpropagation method by changing the connection weights.
- connection weights between the processing elements contain information relating to the relationship between measured radiological recordings and artificially generated radiological recordings which simulate radiological recordings after the application of a blood pool contrast agent. This information can be used to predict at least one artificial radiological uptake for at least one new measured radiological uptake.
- a cross-validation method can be used to split the data into training and validation records.
- the training data set is used in backpropagation training of the network weights.
- the validation data set is used to check the predictive accuracy with which the trained network can be applied to unknown (new) radiological images.
- a blood pool contrast agent does not necessarily have to be / has been applied in order to generate a training and validation data set. It is also conceivable that another contrast medium, preferably an extracellular contrast medium, is used to generate a training and validation data set.
- the contrast agent even if it is not a blood pool contrast agent, remains in the blood vessel system of the examination subject for a certain time. This time can be sufficient to record radiological recordings (by measurement) that show an examination area in which blood vessels have a high contrast to the surrounding tissue. These recorded recordings can then, if necessary after processing to compensate for the decrease in contrast enhancement over time, be used for training and validating a prediction model.
- examination object As already indicated, further information on the examination object, the examination area and / or examination conditions can also be used for training and validating a prediction model and for generating predictions with the prediction model.
- Examples of information on the examination subject are: gender, age, weight, height, anamnesis, type and duration and amount of medication already taken, blood pressure, central venous pressure, respiratory rate, serum albumin, total bilirubin, blood sugar, iron content, respiratory capacity and the like. These can also be used, for example, in a database or an electronic patient file.
- Examples of information about the examination area are: previous illnesses, operations, partial resection, liver transplantation, iron liver, fatty liver and the like.
- the prediction model is preferably trained to distinguish between different blood vessels, for example arteries from veins. This can be done, for example, by a radiologist marking the respective blood vessels differently in the radiological recordings that are used for training. It is also conceivable that the prediction model learns to differentiate between the different blood vessels on the basis of the dynamics in a sequence of radiological recordings after the application of a contrast agent. After an application in the form of a bolus, the contrast agent is not immediately present in all blood vessels in the same concentration, but is distributed from the application site in the blood vessel system with the blood flow. Depending on the application site, it is initially through the arteries or the veins directed. The prediction model can therefore learn to differentiate between different blood vessels on the basis of the dynamic behavior of the contrast agent applied.
- An artificial radiological recording can therefore also be generated by adding several measured radiological recordings that show the examination area at different times after the application of the contrast agent. It is conceivable, for example, that a first measured radiological recording shows an arterial phase, while a second measured radiological recording shows a venous phase. These two measured radiological recordings (and possibly further radiological recordings) can be added together. The addition can take place pixel by pixel or voxel by voxel. For example, the gray values of the pixels can be added (in pairs). A subsequent normalization can be used to ensure that the gray values are again in the usual range (e.g. from 0 to 255).
- a pixel or a voxel of a recording corresponds to exactly one pixel or voxel of a subsequent recording and / or a previous recording: the corresponding (corresponding) pixels or voxels show the same examination area different times.
- the mathematical operations described in this description can be carried out with the pairs of corresponding pixels or voxels to calculate artificial radiological recordings. If the examination object has moved between radiological recordings that follow one another in time, a movement correction must be carried out before the described calculations are carried out. Motion correction methods are described in the prior art (see for example: EP3118644, EP3322997, US20080317315, US20170269182, US20140062481, EP2626718).
- the artificial radiological recordings produced according to the invention can be displayed on a monitor, output on a printer and / or stored in a data memory.
- Artificial radiological recordings are preferably generated automatically and output (preferably displayed) in quasi real time in addition to the corresponding measured radiological recordings or instead of the measured radiological recordings.
- a blood vessel model is generated on the basis of the measured radiological recordings.
- the blood vessel model is a digital representation of the examination subject or a part thereof (preferably of the examination area), structures that can be traced back to blood vessels being identified in the representation, or the representation only contains structures that can be traced back to blood vessels.
- the blood vessel model is preferably a three-dimensional representation in which the spatial course of blood vessels is marked / recorded. Different types of blood vessels (e.g. arteries and veins) are preferably labeled differently.
- the blood vessel model is generated on the basis of at least one measured native image and at least one measured radiological image after the application of a contrast agent.
- the at least one native image shows an examination area of the examination subject without contrast agent.
- the at least one Radiological image after application of a contrast agent preferably shows the same area, with some or all of the blood vessels in the area being contrast-enhanced.
- the blood vessel model can be generated by subtracting a native image from a measured radiological image after applying a contrast agent and then normalizing it.
- the subtraction is preferably carried out pixel by pixel or voxel by voxel.
- the gray values of the pixels can be subtracted from one another.
- the subsequent normalization is used to ensure that the gray values are again in the usual range (e.g. from 0 to 255) and that there are no negative gray values.
- the blood vessel model can also be generated by adding a plurality of measured radiological recordings after application of a spreading contrast agent and subsequent normalization.
- the addition is preferably carried out pixel by pixel or voxel by voxel.
- the gray values of the pixels can be added in pairs.
- the subsequent normalization is used to ensure that the gray values are again in the usual range (e.g. from 0 to 255).
- Structures in the blood vessel model that cannot be traced back to blood vessels are preferably removed: if blood vessels are shown brightly, for example, then all pixels (or voxels) whose gray values are below a threshold value can be set to the gray value zero; If, on the other hand, blood vessels are shown dark, then all pixels (or voxels) whose gray values are above a threshold value can be set to the highest gray value (e.g. 255). In this way, structures that do not originate from blood vessels are reduced (in contrast) or completely eliminated.
- the blood vessel model can also be obtained from measured radiological recordings by other segmentation methods. Segmentation methods are widely described in the literature. The following publications are listed as examples: F. Conversano et al .: Hepatic Vessel Segmentation for 3D Planning of Liver Surgery, Acad Radiol 2011, 18: 461-470; S. Moccia et al .: Blood vessel Segmentation algorithms - Review of methods, datasets and evaluation metrics, Computer Methods and Programs in Biomedicine 158 (2018) 71-91; M. Marcan et al .: Segmentation of hepatic vessels from MRI images for planning of electroporation-based treatments in the liver, Radiol Oncol 2014; 48 (3): 267-281; T.A.
- the blood vessel model is preferably available in the same digital (data) format as the at least one measured radiological image after application of a contrast agent and / or as the at least one native radiological image. If the same digital format is available, calculations can be carried out more easily using the corresponding files; in particular, the blood vessel model can be generated more easily from the measured radiological recordings.
- the blood vessel model can be used and output directly as an artificial radiological recording. However, it is also conceivable that the blood vessel model is overlaid with one or more measured radiological recordings in order to generate one or more artificial radiological recordings. It can be overlaid with a native image, for example, in order to display the blood vessels in the native image. Different blood vessels can preferably be faded in and out independently of one another.
- the blood vessel model can also be overlaid with at least one measured radiological image after application of a contrast agent.
- the overlay with a radiological image after application of a contrast agent is advantageous, for example, if small focal liver lesions are to be identified during an MRI examination of the liver (see e.g. P. Bannas: Combined Gadoxetic Acid and Gadofosveset Enhanced MRI: A Feasibility and Parameter Optimization Study, Magnetic Resonance in Medicine 75: 318-328 (2016)). It can be difficult to distinguish liver lesions from blood vessel structures on an MRI scan.
- the simulation according to the invention of a blood pool contrast agent can provide a remedy here.
- different larb values are preferably selected for different types of blood vessels (e.g. arteries and veins) (lalsch color display).
- arteries can be identified by a first larb value (e.g. a larb value for a red larb) and veins by a second larb value (e.g. a larb value for a blue larb).
- the pixels or voxels that represent blood vessels in the blood vessel model can preferably be faded in continuously into the at least one measured radiological image using a (virtual) slider, the corresponding pixels or voxels in the artificial radiological image thus generated when fading in increasingly assume the larb values of the pixels or voxels of the blood vessel model.
- types of blood vessels can be displayed independently of one another (e.g. arteries independent of veins and / or veins independent of arteries).
- the possibility of switching the structures originating from blood vessels or types of blood vessels on and off instead of fading in or in addition to fading in is also conceivable.
- a radiologist can make blood vessels or types of blood vessels visible in a measured radiological image in order to be able to assign structures in the radiological images.
- a computer-implemented method comprising the steps
- At least one radiological recording wherein the at least one radiological recording shows an examination area of an examination subject, calculating at least one artificial radiological recording on the basis of the at least one radiological recording, blood vessels in the at least one artificial radiological recording being shown in contrast to the surrounding tissue, outputting the at least one artificial radiological recording.
- Receiving at least one measured radiological recording, the at least one measured radiological recording showing an examination area of an examination subject Feeding the at least one measured radiological recording to a prediction model, the prediction model being trained on the basis of reference data in a monitored learning process to generate at least one artificial radiological recording for at least one measured radiological recording showing an examination area of an examination subject, the at least one artificial radiological image shows the examination area after application of a blood pool contrast agent, receiving at least one artificial radiological image from the prediction model, the at least one artificial radiological image showing the examination area after application of a blood pool contrast agent,
- the at least one measured radiological image is a radiological image or comprises an image that shows an examination area of an examination subject after application of a contrast agent
- the prediction model being trained on the basis of reference data in a monitored learning process to generate at least one artificial radiological recording for at least one measured radiological recording which shows an examination area of an examination subject after application of a contrast agent, wherein the at least one artificial radiological image shows the examination area after application of a blood pool contrast agent,
- Radiological recordings Receiving a plurality of measured radiological recordings, the radiological recordings showing an examination area at different times after a contrast agent has been applied,
- the prediction model Feeding the plurality of measured radiological recordings to a prediction model, the prediction model being trained on the basis of reference data in monitored learning, for a plurality of measured radiological recordings showing an examination area at different times after application of a contrast agent, at least one artificial radiological recording to generate, wherein the at least one artificial radiological recording shows blood vessels in the examination area with increased contrast and with a constant contrast over time compared to the surrounding tissue,
- the at least one artificial radiological recording receiving at least one artificial radiological recording from the prediction model, the at least one artificial radiological recording showing blood vessels in the examination area in a contrast-enhanced manner and with a contrast that remains constant over time in relation to the surrounding tissue,
- At least one artificial radiological recording the at least one artificial radiological recording showing the same examination area, blood vessels in the examination area being shown with a contrast enhancement compared to the surrounding tissue, the contrast enhancement not decreasing over time,
- Radiological recordings Receiving a plurality of measured radiological recordings, the radiological recordings showing an examination area at different times after a contrast agent has been applied,
- Radiological recordings Receiving a plurality of measured radiological recordings, the radiological recordings showing an examination area at different times before and / or after an application of a contrast agent
- the blood vessel model being a representation of the examination area, structures that can be traced back to blood vessels in the examination area being identified in the blood vessel model,
- a computer system comprising a receiving unit, a control and computing unit and an output unit wherein the control and processing unit is configured to cause the receiving unit to receive at least one radiological recording, the at least one radiological recording showing an examination area of an examination subject, the control and processing unit being configured based on the at least one radiological recording at least one to calculate artificial radiological recording, blood vessels in the at least one artificial radiological recording being shown with a contrast-enhanced contrast to surrounding tissue, the control and computing unit being configured to cause the output unit to output the at least one artificial radiological recording.
- control and computing unit is configured to cause the receiving unit to receive at least one first measured radiological image of a blood vessel system of an examination subject or a part of the blood vessel system, the control and computing unit being configured to generate a model of the blood vessel system or a part thereof on the basis of the at least one first measured radiological image, wherein the control and computing unit is configured to cause the receiving unit to receive at least one second measured radiological image of an examination area of the examination subject, wherein the control and arithmetic unit is configured to generate at least one third radiological record by superimposing the at least one second radiological record with the model of the blood vessel system or a part thereof, the control and arithmetic units it is configured to cause the output unit to output the at least one third radiological recording.
- a computer program product comprising a computer program that can be loaded into a main memory of a computer and there causes the computer to carry out the following steps:
- At least one radiological recording wherein the at least one radiological recording shows an examination area of an examination subject, calculating at least one artificial radiological recording based on the at least one radiological recording, blood vessels in the at least one artificial radiological recording being shown in contrast to the surrounding tissue, outputting the at least one artificial radiological recording.
- Generating at least one artificial radiological recording by superimposing the at least one radiological recording with the model of the blood vessel system or a part thereof Outputting the at least one artificial radiological recording.
- a contrast agent for use in a radiological examination procedure comprising the following steps:
- Generating at least one artificial radiological recording by superimposing the at least one radiological recording with the model of the blood vessel system or a part thereof
- a kit comprising a contrast agent and a computer program product according to the invention according to embodiment 13 above.
- FIG. 1 shows schematically and by way of example an embodiment of the computer system according to the invention.
- the computer system (10) comprises a receiving unit (11), a control and computing unit (12) and an output unit (13).
- a “computer system” is a system for electronic data processing that processes data using programmable arithmetic rules.
- Such a system usually comprises a control and arithmetic unit, often also referred to as a “computer”, that unit which comprises a processor for performing logical operations and a working memory for loading a computer program, as well as peripherals.
- peripherals are all devices that are connected to the computer and are used to control the computer and / or as input and output devices. Examples of this are monitors (screens), printers, scanners, mice, keyboards, joysticks, drives, cameras, microphones, loudspeakers, etc. Internal connections and expansion cards are also considered peripherals in computer technology.
- Today's computer systems are often divided into desktop PCs, portable PCs, laptops, notebooks, netbooks and tablet PCs and so-called handheids (e.g. smartphones); any of these systems can be used to practice the invention.
- Inputs into the computer system are made via input means such as a keyboard, a mouse, a microphone, a touch-sensitive display and / or the like.
- Outputs take place via the output unit (13), which can in particular be a monitor (screen), a printer and / or a data memory.
- the computer system (10) is configured to receive measured radiological recordings and to generate (calculate) artificial radiological recordings on the basis of the received radiological recordings.
- the control and computing unit (12) is used to control the receiving unit (11) and the output unit (13) and to coordinate the data and signal flows between the various Units, the processing of radiological recordings and the generation of artificial radiological recordings. It is conceivable that there are several control and computing units.
- the receiving unit (11) is used to receive radiological recordings.
- the radiological recordings can for example be transmitted by a magnetic resonance tomograph or transmitted by a computer tomograph or read out from a data memory.
- the magnetic resonance tomograph or the computed tomograph can be a component of the computer system according to the invention.
- the computer system according to the invention is a component of a magnetic resonance tomograph or a computed tomograph.
- the transmission of radiological recordings can take place via a network connection or a direct connection.
- the transmission of radiological recordings can take place via a radio connection (WLAN, Bluetooth, cellular radio and / or the like) and / or wired. It is conceivable that there are several receiving units.
- the data memory can also be part of the computer system according to the invention or be connected to it via a network, for example. It is conceivable that there are several data stores.
- the receiving unit receives the radiological recordings, if necessary, further data (such as information on the examination subject, recording parameters and / or the like) and transmits them to the control and computing unit.
- the control and computing unit is configured to generate artificial radiological recordings based on the received data.
- the artificial radiological recordings can be displayed (for example on a monitor), output (e.g. via a printer) or saved in a data memory via the output unit (13). It is conceivable that there are several output units.
- FIG. 2 shows, by way of example and schematically, an embodiment of the method (100) according to the invention or the steps carried out by the computer program product according to the invention in the form of a flowchart.
- the steps are:
- FIG. 3 shows, by way of example and schematically, a preferred embodiment of the method (200) according to the invention or the steps carried out by the computer program product according to the invention in the form of a flowchart.
- the steps are: (210) Receiving a sequence of measured radiological recordings, the measured radiological recordings showing an examination area of an examination subject at different, successive points in time after an application of a contrast agent, the contrast agent leading to a contrast enhancement of blood vessels in the measured radiological recordings of the examination area, the contrast enhancement of the blood vessels in the measured radiological images decreases with increasing time,
- (220) supplying the radiological recordings to an artificial neural network, the artificial neural network having been trained on the basis of reference data in a monitored learning process to compensate for a decrease in contrast enhancement of blood vessels in radiological recordings,
- FIGS. 4 (a), (b) and (c) show exemplary and schematic radiological recordings of a liver after intravenous application of a contrast agent into an arm vein of an examination subject.
- FIGS. 4 (a), 4 (b) and 4 (c) the same cross section through the liver (L) is always shown at different, successive points in time.
- the reference symbols drawn in FIGS. 4 (a), 4 (b) and 4 (c) apply to all FIGS. 4 (a), 4 (b) and 4 (c); they are only shown once for the sake of clarity.
- FIGS. 4 (a), 4 (b) and 4 (c) the arteries (A) and veins (V) are shown in contrast to the surrounding tissue (liver cells). However, the contrast enhancement decreases with time from Fig. 4 (a) to Fig. 4 (b) to Fig. 4 (c).
- FIG. 5 schematically shows, by way of example, the generation of artificial radiological recordings on the basis of measured radiological recordings with the aid of a prediction model (PM).
- PM prediction model
- Radiological images (a), (b) and (c) of a liver shown in FIG. 5 correspond to the images of the liver shown in FIGS. 4 (a), 4 (b) and 4 (c). These measured radiological recordings (a), (b) and (c) are fed to a prediction model (PM). The prediction model generates three artificial radiological recordings (a ‘), (b‘) and (c ‘) from the three measured radiological recordings (a), (b) and (c). While the contrast enhancement of the blood vessels (arteries A and veins V) decreases over time in the measured radiological images, it remains the same over time in the artificially generated radiological images.
- FIGS. 6 (a), 6 (b) and 6 (c) show exemplary and schematic radiological images of a liver before (6 (a)) and after (6 (b), 6 (c)) the intravenous application of a contrast agent in a Arm vein of an examination subject.
- FIGS. 6 (a), 6 (b) and 6 (c) the same cross section through the liver (L) is always shown at different, successive points in time.
- FIGS. 6 (a), 6 (b) and 6 (c) apply to all FIGS. 6 (a), 6 (b) and 6 (c); they are only shown once for the sake of clarity.
- 6 (a) shows the cross section through the liver (L) before the intravenous application of a contrast medium.
- a contrast agent was administered intravenously as a bolus. This reaches the liver in FIG. 6 (b) via the hepatic artery (A).
- the hepatic artery is shown with an enhanced signal (arterial phase).
- the contrast agent reaches the liver via the veins (venous phase).
- FIG. 6 (a) is therefore a native radiological image
- FIG. 6 (b) is a first radiological image after application of a contrast agent
- FIG. 6 (c) is a second radiological image after application of the contrast agent.
- the arteries can be seen particularly well, while the veins can be seen particularly well in FIG. 6 (c).
- FIG. 7 shows by way of example and schematically the generation of an artificial radiological recording (AI) on the basis of measured radiological recordings with the aid of a prediction model (PM).
- the prediction model (PM) is trained to generate at least one artificial radiological image for at least one measured radiological image that shows an examination area of an examination subject, which shows the examination area after the application of an intravascular contrast agent.
- the radiological recordings from FIGS. 6 (b) and 6 (c) are fed to the prediction model (PM).
- the prediction model then automatically generates an artificial radiological image (AI). This shows all blood vessels (arteries A, veins V) with increased contrast and with constant contrast over time compared to the surrounding tissue.
- FIG. 8 shows, by way of example and schematically, the generation of a blood vessel model from measured radiological recordings.
- Figures 8 (a), 8 (b) and 8 (c) are identical to Figures 6 (a), 6 (b) and 6 (c).
- the native radiological image in FIG. 8 (a) is combined with the radiological image in FIG. 8 (b) and the radiological image in FIG. 8 (c) to form a blood vessel model (FIG. 8 (d)).
- a difference image is generated from FIG. 8 (a) and FIG. 8 (b) (FIGS. 8 (b) -8 (a)).
- the arteries (A) stand out particularly strongly, while all other structures are in the background.
- a difference image of FIGS. 8 (a) and 8 (c) can be generated (FIGS. 8 (c) -8 (a)).
- the veins (V) are particularly prominent, while all other structures take a back seat.
- the two difference images generated can be combined, e.g. by addition, to form the blood vessel model (Fig. 8 (d)).
- the arteries and the veins in the blood vessel model (FIG. 8 (d)) are preferably identified differently (in the present case the veins are provided with horizontal hatching, while the arteries are provided with vertical hatching).
- FIG. 9 shows, by way of example and schematically, a measured radiological image of a liver (L) after the intravenous application of a hepatobiliary contrast agent into an arm vein of the examination subject.
- the hepatobiliary contrast agent is absorbed by healthy liver cells.
- the radiological image shown in FIG. 9 shows the liver in a cross section in the hepatobiliary phase in which the liver cells have already absorbed contrast medium.
- a structure T can be seen for which it is unclear whether it is a blood vessel or a tumor.
- FIG. 10 shows, by way of example and schematically, the superposition of a measured radiological image with a blood vessel model to form an artificial radiological image.
- Fig. 10 (a) shows the measured radiological image of a liver (L) in cross section.
- Fig. 10 (a) is identical to Fig. 9.
- Fig. 10 (b) shows a blood vessel model.
- Fig. 10 (b) is identical to Fig. 8 (d).
- Fig. 10 (c) shows an artificial radiological photograph.
- the pixels of those structures of the blood vessel model that can be traced back to blood vessels replace the corresponding (corresponding) pixels of the measured radiological recording.
- the artificial radiological image clearly shows which structures are due to healthy liver cells, which structures are due to arteries (A) and which structures are due to veins (V). Furthermore, it can be seen in the artificial radiological image that the structure T is not a blood vessel. It is conceivable that there is a tumor.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Medical Informatics (AREA)
- Radiology & Medical Imaging (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Theoretical Computer Science (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- Computer Vision & Pattern Recognition (AREA)
- High Energy & Nuclear Physics (AREA)
- Signal Processing (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
Description
Claims
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP20167879 | 2020-04-03 | ||
| EP20204511 | 2020-10-29 | ||
| PCT/EP2021/057689 WO2021197996A1 (de) | 2020-04-03 | 2021-03-25 | Erzeugen von radiologischen aufnahmen |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4128261A1 true EP4128261A1 (de) | 2023-02-08 |
Family
ID=75143664
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP21713686.0A Pending EP4128261A1 (de) | 2020-04-03 | 2021-03-25 | Erzeugen von radiologischen aufnahmen |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US12394058B2 (de) |
| EP (1) | EP4128261A1 (de) |
| JP (1) | JP7729836B2 (de) |
| CN (1) | CN115398555A (de) |
| CA (1) | CA3177210A1 (de) |
| WO (1) | WO2021197996A1 (de) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3939003B1 (de) | 2019-03-12 | 2024-04-03 | Bayer HealthCare, LLC | Systeme und verfahren zur beurteilung der wahrscheinlichkeit von cteph und identifizierung von darauf hinweisenden merkmalen |
| EP4231037A1 (de) | 2019-09-18 | 2023-08-23 | Bayer Aktiengesellschaft | Beschleunigung von mrt-untersuchungen |
| JP7535575B2 (ja) | 2019-09-18 | 2024-08-16 | バイエル、アクチエンゲゼルシャフト | 組織特性を予測、予想、および/または査定するためのシステム、方法、およびコンピュータプログラム製品 |
| EP4031893B1 (de) | 2019-09-18 | 2024-12-25 | Bayer Aktiengesellschaft | Erzeugung von mrt-aufnahmen der leber |
| EP4128261A1 (de) | 2020-04-03 | 2023-02-08 | Bayer Aktiengesellschaft | Erzeugen von radiologischen aufnahmen |
| WO2024046832A1 (de) * | 2022-08-30 | 2024-03-07 | Bayer Aktiengesellschaft | Erzeugen von synthetischen radiologischen aufnahmen |
| EP4336513B1 (de) | 2022-08-30 | 2024-12-18 | Bayer Aktiengesellschaft | Erzeugen von synthetischen radiologischen aufnahmen |
| WO2024046833A1 (de) | 2022-08-30 | 2024-03-07 | Bayer Aktiengesellschaft | Erzeugen von synthetischen radiologischen aufnahmen |
| WO2024046831A1 (de) * | 2022-08-30 | 2024-03-07 | Bayer Aktiengesellschaft | Erzeugen von synthetischen radiologischen aufnahmen |
| EP4369353A1 (de) * | 2022-11-12 | 2024-05-15 | Bayer Aktiengesellschaft | Erzeugung von künstlichen kontrastmittelverstärkten radiologischen aufnahmen |
| EP4571650A1 (de) | 2023-12-12 | 2025-06-18 | Bayer AG | Erzeugung synthetischer bilder |
| EP4575997A1 (de) | 2023-12-18 | 2025-06-25 | Bayer Aktiengesellschaft | Erzeugung synthetischer bilder |
Family Cites Families (118)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US732697A (en) | 1903-02-19 | 1903-07-07 | John Davis Bates | Lumber-surface meter. |
| US6039931A (en) | 1989-06-30 | 2000-03-21 | Schering Aktiengesellschaft | Derivatized DTPA complexes, pharmaceutical agents containing these compounds, their use, and processes for their production |
| US6397098B1 (en) | 1994-09-21 | 2002-05-28 | Medrad, Inc. | Data communication and control for medical imaging systems |
| US5840026A (en) | 1994-09-21 | 1998-11-24 | Medrad, Inc. | Patient specific dosing contrast delivery systems and methods |
| US5732697A (en) | 1995-11-22 | 1998-03-31 | Arch Development Corporation | Shift-invariant artificial neural network for computerized detection of clustered microcalcifications in mammography |
| US6339718B1 (en) | 1999-07-30 | 2002-01-15 | Medrad, Inc. | Programmable injector control |
| US6754376B1 (en) | 2000-11-22 | 2004-06-22 | General Electric Company | Method for automatic segmentation of medical images |
| EP1345154A1 (de) | 2002-03-11 | 2003-09-17 | Bracco Imaging S.p.A. | Verfahren zur Kodierung von Bildpunkten und Verfahren zur Bildverarbeitung das dazu geignet ist, eine qualitative Erkennung eines mit einem oder mehreren Bildpunkten reproduzierten Objektes zu führen |
| US6819790B2 (en) | 2002-04-12 | 2004-11-16 | The University Of Chicago | Massive training artificial neural network (MTANN) for detecting abnormalities in medical images |
| US7458936B2 (en) | 2003-03-12 | 2008-12-02 | Siemens Medical Solutions Usa, Inc. | System and method for performing probabilistic classification and decision support using multidimensional medical image databases |
| US7221408B2 (en) * | 2003-08-15 | 2007-05-22 | Samsung Electronics Co., Ltd. | Adaptive contrast enhancement method for video signals based on time-varying nonlinear transforms |
| US7545965B2 (en) | 2003-11-10 | 2009-06-09 | The University Of Chicago | Image modification and detection using massive training artificial neural networks (MTANN) |
| US20060018524A1 (en) | 2004-07-15 | 2006-01-26 | Uc Tech | Computerized scheme for distinction between benign and malignant nodules in thoracic low-dose CT |
| WO2006036842A2 (en) | 2004-09-24 | 2006-04-06 | The University Of North Carolina At Chapel Hill | Methods, systems, and computer program products for hierarchical registration between a blood vessel and tissue surface model for a subject and blood vessel and tissue surface image for the subject |
| US8295914B2 (en) | 2004-11-16 | 2012-10-23 | Medrad, Inc. | Systems and methods of determining patient transfer functions and modeling patient response to a pharmaceutical injection |
| US7853309B2 (en) * | 2005-03-10 | 2010-12-14 | Toshiba Medical Systems Corporation | X-ray CT apparatus and myocardial perfusion image generating system |
| US7738683B2 (en) | 2005-07-22 | 2010-06-15 | Carestream Health, Inc. | Abnormality detection in medical images |
| US7564990B2 (en) | 2005-08-18 | 2009-07-21 | Nu Skin International, Inc. | Imaging system and method for physical feature analysis |
| US7343032B2 (en) | 2005-09-01 | 2008-03-11 | Fujifilm Corporation | Method and apparatus for automatic and dynamic vessel detection |
| EP1780651A1 (de) * | 2005-10-25 | 2007-05-02 | Bracco Imaging, S.P.A. | Verfahren und System zur automatischen Verarbeitung und Bewertung von Bildern, im Besonderen diagnostischer Bilder |
| EP1780677A1 (de) | 2005-10-25 | 2007-05-02 | BRACCO IMAGING S.p.A. | Bildverarbeitungssystem, im Besonderen zur Verwendung für diagnostische Bilder |
| CN107358595B (zh) | 2005-11-01 | 2021-09-03 | 美国医软科技公司 | 用于肝叶分割和术前手术规划的方法和系统 |
| US20220031270A1 (en) | 2007-03-08 | 2022-02-03 | Sync-Rx, Ltd | Identification an dpresentation of device-tovessel relative motion |
| WO2009020687A2 (en) | 2007-05-18 | 2009-02-12 | Henry Ford Health System | Mri estimation of contrast agent concentration using a neural network approach |
| DE102007028660B3 (de) | 2007-06-21 | 2009-01-29 | Siemens Ag | Verfahren zur Korrektur von Bewegungsartefakten bei der Aufnahme von MR-Bildern |
| US20090143669A1 (en) | 2007-12-04 | 2009-06-04 | Harms Steven E | Color mapped magnetic resonance imaging |
| CN101938939B (zh) | 2008-02-07 | 2014-11-26 | 皇家飞利浦电子股份有限公司 | 用于测量和预测患者呼吸稳定性的装置 |
| US8428327B2 (en) | 2008-05-08 | 2013-04-23 | Oslo Universitetssykehus Hf | Vessel segmentation in DCE MR imaging |
| US7949167B2 (en) | 2008-06-12 | 2011-05-24 | Siemens Medical Solutions Usa, Inc. | Automatic learning of image features to predict disease |
| US20130035921A1 (en) | 2010-01-28 | 2013-02-07 | Maria Inmaculada Rodriguez-Ponce | Method and apparatus for estimating temperature in a body |
| US8478698B1 (en) | 2010-03-17 | 2013-07-02 | James Mah | Methods and systems for employing artificial intelligence in automated orthodontic diagnosis and treatment planning |
| JP5917552B2 (ja) | 2010-12-08 | 2016-05-18 | べイヤー ヘルスケア、エルエルシー | 医療用撮像スキャンによって患者が受ける放射線量に関する予測の作成 |
| FR2979453B1 (fr) | 2011-08-26 | 2016-01-08 | Olea Medical | Systeme et procede pour estimer une quantite d'interet d'un systeme dynamique artere/tissu/veine |
| WO2013036842A2 (en) | 2011-09-08 | 2013-03-14 | Radlogics, Inc. | Methods and systems for analyzing and reporting medical images |
| JP5878009B2 (ja) | 2011-12-12 | 2016-03-08 | 株式会社根本杏林堂 | 医療用画像処理ネットワークシステム |
| WO2016007734A1 (en) | 2014-07-09 | 2016-01-14 | The Trustees Of Dartmouth College | Methods for quantitative and enhanced-contrast molecular medical imaging using cross-modality correction for differing tracer kinetics |
| EP2626718A1 (de) | 2012-02-09 | 2013-08-14 | Koninklijke Philips Electronics N.V. | Magnetresonanzbildgebung mit Bewegungskorrektur unter Verwendung von Navigatoren, welche mit einem Dixon-Verfahren erhalten wurden |
| EP2815343A2 (de) | 2012-02-17 | 2014-12-24 | Koninklijke Philips N.V. | Beurteilung und überwachung von akuten lungenverletzungen (ali)/akutem lungenversagen (ards) |
| US20150125398A1 (en) | 2012-05-11 | 2015-05-07 | University Of Iowa Research Foundation | Multimodal imaging methods using mesoporous silica nanoparticles |
| DE102012215718B4 (de) | 2012-09-05 | 2022-05-12 | Siemens Healthcare Gmbh | Verfahren und Magnetresonanzanlage zur MR-Bildgebung eines vorbestimmten Volumenabschnitts eines lebenden Untersuchungsobjekts mittels Stimulieren des Untersuchungsobjekts |
| US9449381B2 (en) | 2012-09-10 | 2016-09-20 | Arizona Board Of Regents, A Body Corporate Of The State Of Arizona, Acting For And On Behalf Of Arizona State University | Methods, systems, and media for generating and analyzing medical images having elongated structures |
| CN104769641B (zh) | 2012-10-31 | 2018-01-26 | 皇家飞利浦有限公司 | 灌注成像 |
| EP2750102B2 (de) | 2012-12-27 | 2025-12-10 | General Electric Company | Verfahren, System und computerlesbares Medium zur Leberanalyse |
| JP6382232B2 (ja) | 2013-02-21 | 2018-08-29 | ユニバ−シティ オブ ロチェスタ− | 脳全体の傍血管経路を老廃物のクリアランス機能について評価するための方法、およびそれに基づいて神経変性障害を治療するための方法 |
| CN105103191B (zh) | 2013-04-03 | 2019-05-10 | 皇家飞利浦有限公司 | 血管分割 |
| EP2988668B1 (de) | 2013-04-24 | 2019-07-24 | Tel HaShomer Medical Research Infrastructure and Services Ltd. | Magnetresonanzkarten zur analyse von gewebe |
| JP6338849B2 (ja) | 2013-12-11 | 2018-06-06 | キヤノンメディカルシステムズ株式会社 | 画像解析装置、及び、x線診断装置 |
| WO2016019347A1 (en) | 2014-07-31 | 2016-02-04 | California Institute Of Technology | Multi modality brain mapping system (mbms) using artificial intelligence and pattern recognition |
| US20160038092A1 (en) | 2014-08-11 | 2016-02-11 | Douglas A. Golay | Applying non-real time and non-user attended algorithms to stored non-imaging data and existing imaging data for obtaining a dental diagnosis |
| US10061003B2 (en) | 2014-09-01 | 2018-08-28 | bioProtonics, L.L.C. | Selective sampling for assessing structural spatial frequencies with specific contrast mechanisms |
| EP3207522A4 (de) | 2014-10-13 | 2018-06-13 | Agency For Science, Technology And Research | Automatische segmentierung eines interessensbereiches und aufnahme von dynamischen, kontrastverstärkten bildern von kolorektalkarzinomen |
| JP6740136B2 (ja) | 2014-11-27 | 2020-08-12 | 国立大学法人広島大学 | シミュレータ、該シミュレータを備える注入装置又は撮像システム、及びシミュレーションプログラム |
| WO2016138449A1 (en) | 2015-02-27 | 2016-09-01 | Bayer Healthcare Llc | Quantification phantom for use with multiple imaging modalities |
| US9959615B2 (en) | 2015-07-01 | 2018-05-01 | Arizona Board Of Regents On Behalf Of Arizona State University | System and method for automatic pulmonary embolism detection |
| US20170016972A1 (en) | 2015-07-13 | 2017-01-19 | Siemens Medical Solutions Usa, Inc. | Fast Prospective Motion Correction For MR Imaging |
| US10634753B2 (en) | 2015-07-15 | 2020-04-28 | Koninklijke Philips N.V. | MR imaging with motion detection |
| US10157467B2 (en) | 2015-08-07 | 2018-12-18 | Arizona Board Of Regents On Behalf Of Arizona State University | System and method for detecting central pulmonary embolism in CT pulmonary angiography images |
| US10176408B2 (en) | 2015-08-14 | 2019-01-08 | Elucid Bioimaging Inc. | Systems and methods for analyzing pathologies utilizing quantitative imaging |
| WO2017035097A1 (en) | 2015-08-21 | 2017-03-02 | Duke University | Systems and methods for determining image quality and models based on contrast injection protocols |
| CN112999464B (zh) | 2015-08-28 | 2023-04-18 | 拜耳医药保健有限公司 | 针筒流体填充验证以及动力注射器系统特征的图像识别的系统和方法 |
| DE102015217141A1 (de) * | 2015-09-08 | 2017-03-09 | Siemens Healthcare Gmbh | Erzeugen von kontrastverstärkten Bilddaten von zu untersuchendem Brustgewebe |
| EP3383441A1 (de) | 2015-11-30 | 2018-10-10 | GE Healthcare AS | Formulierungen mit einer kombination aus mrt-kontrastmitteln |
| US10645359B2 (en) | 2015-12-16 | 2020-05-05 | B<>Com | Method for processing a digital image, device, terminal equipment and associated computer program |
| US9786058B2 (en) | 2016-02-08 | 2017-10-10 | Sony Corporation | Method and system for segmentation of vascular structure in a volumetric image dataset |
| US20170245817A1 (en) | 2016-02-10 | 2017-08-31 | The Charles Stark Draper Laboratory, Inc. | Systems and methods for imaging |
| DE102016204198B4 (de) | 2016-03-15 | 2018-06-07 | Siemens Healthcare Gmbh | Verfahren zur Erzeugung von MR-Bildern mit prospektiver Bewegungskorrektur und teilvolumenspezifischer Gewichtung der Bildinformation |
| US10282588B2 (en) | 2016-06-09 | 2019-05-07 | Siemens Healthcare Gmbh | Image-based tumor phenotyping with machine learning from synthetic data |
| CN110234400B (zh) * | 2016-09-06 | 2021-09-07 | 医科达有限公司 | 用于生成合成医学图像的神经网络 |
| US11544529B2 (en) | 2016-09-07 | 2023-01-03 | Koninklijke Philips N.V. | Semi-supervised classification with stacked autoencoder |
| WO2018075386A1 (en) | 2016-10-17 | 2018-04-26 | Bayer Healthcare Llc | Fluid injector with syringe engagement mechanism |
| US10933186B2 (en) | 2016-11-22 | 2021-03-02 | Bayer Healthcare Llc | System and method for delivering a fluid with a consistent total volumetric flowrate |
| CN109983474A (zh) | 2016-11-22 | 2019-07-05 | 海珀菲纳研究股份有限公司 | 用于磁共振图像中的自动检测的系统和方法 |
| JP7098356B2 (ja) | 2017-03-09 | 2022-07-11 | ゼネラル・エレクトリック・カンパニイ | Ct画像の色の視覚化のためのシステムおよび方法 |
| US10096109B1 (en) | 2017-03-31 | 2018-10-09 | The Board Of Trustees Of The Leland Stanford Junior University | Quality of medical images using multi-contrast and deep learning |
| JP7179757B2 (ja) | 2017-04-25 | 2022-11-29 | ザ ボード オブ トラスティーズ オブ ザ レランド スタンフォード ジュニア ユニバーシティー | ディープ畳み込みニューラルネットワークを使用した医用画像化のための線量低減 |
| US20180315183A1 (en) | 2017-04-28 | 2018-11-01 | General Electric Company | System and method for monitoring an amount of a contrast agent within an object |
| WO2018202541A1 (de) | 2017-05-02 | 2018-11-08 | Bayer Aktiengesellschaft | Verbesserungen bei der radiologischen erkennung chronisch thromboembolischer pulmonaler hypertonie |
| US10769823B2 (en) * | 2017-06-22 | 2020-09-08 | Canon Medical Systems Corporation | Image processing apparatus, magnetic resonance imaging apparatus, and storage medium |
| JP6920904B2 (ja) | 2017-07-04 | 2021-08-18 | 国立大学法人広島大学 | シミュレータ、該シミュレータを備える注入装置又は撮像システム、及びシミュレーションプログラム |
| WO2019046299A1 (en) | 2017-08-31 | 2019-03-07 | Bayer Healthcare Llc | FLUID PATH IMPEDANCE ASSESSMENT FOR IMPROVING FLUID DISTRIBUTION PERFORMANCE |
| US11631485B2 (en) | 2017-09-26 | 2023-04-18 | Koninklijke Philips N.V. | System and method for joint clinical decision for pharmaceuticals |
| US10335106B2 (en) | 2017-09-29 | 2019-07-02 | Infinitt Healthcare Co., Ltd. | Computing system and method for identifying and visualizing cerebral thrombosis based on medical images |
| EP3694413B1 (de) | 2017-10-09 | 2025-06-11 | The Board of Trustees of the Leland Stanford Junior University | Kontrastmitteldosisreduktion für medizinische bildgebung unter verwendung von tiefenlernen |
| US11100621B2 (en) * | 2017-10-20 | 2021-08-24 | Imaging Biometrics, Llc | Simulated post-contrast T1-weighted magnetic resonance imaging |
| CN118866316A (zh) | 2017-10-31 | 2024-10-29 | 通用电气健康护理有限公司 | 用于诊断认知疾病病理和/或结果的医疗系统 |
| EP3714784A4 (de) | 2017-11-24 | 2021-08-04 | Canon Medical Systems Corporation | Vorrichtung zur verarbeitung medizinischer daten, magnetresonanzbildgebungsvorrichtung und verfahren zur erzeugung eines erlernten modells |
| CN108324244A (zh) | 2018-01-03 | 2018-07-27 | 华东师范大学 | 用于ai+mri影像辅助诊断的自动增广训练样本的构建方法及系统 |
| KR102001398B1 (ko) | 2018-01-25 | 2019-07-18 | 재단법인 아산사회복지재단 | 기계학습을 통한 뇌질환 상태변화 예측방법, 장치 및 프로그램 |
| CN111656392B (zh) | 2018-02-15 | 2024-01-05 | 通用电气公司 | 用于合成磁共振图像的系统和方法 |
| US11640682B2 (en) | 2018-03-22 | 2023-05-02 | The University Of North Carolina At Chapel Hill | Methods, systems, and computer readable media for processing digital subtraction angiography (DSA) and computed tomography (CT) images for reducing radiation exposure in DSA and CT subjects |
| US11100632B2 (en) | 2018-04-13 | 2021-08-24 | Elekta, Inc. | Image synthesis using adversarial networks such as for radiation therapy |
| US11982726B2 (en) | 2018-04-13 | 2024-05-14 | University Of Southern California | Method for joint arterial input function and tracer kinetic parameter estimation in accelerated DCE-MRI using a model consistency constraint |
| SG11202010238PA (en) | 2018-04-19 | 2020-11-27 | Subtle Medical Inc | Systems and methods for improving magnetic resonance imaging using deep learning |
| CN108703764B (zh) | 2018-05-29 | 2021-11-05 | 北京东软医疗设备有限公司 | 血管造影方法、装置、系统、设备及存储介质 |
| CN112313668A (zh) | 2018-06-15 | 2021-02-02 | 深透医疗公司 | 使用深度学习进行磁共振成像标准化的系统和方法 |
| EP3616620A1 (de) * | 2018-08-28 | 2020-03-04 | Koninklijke Philips N.V. | Spektrale zweischichtige ct-geführte eingriffe |
| US11080895B2 (en) * | 2018-10-30 | 2021-08-03 | International Business Machines Corporation | Generating simulated body parts for images |
| EP3649955A1 (de) | 2018-11-07 | 2020-05-13 | Koninklijke Philips N.V. | Deep learning basierte spektrale bolusverfolgung |
| EP3657433B1 (de) | 2018-11-22 | 2022-10-19 | Siemens Healthcare GmbH | Daten medizinischer bilder |
| DE102018222606A1 (de) | 2018-12-20 | 2020-06-25 | Siemens Healthcare Gmbh | Verfahren und Vorrichtung zur Detektion eines anatomischen Merkmals eines Blutgefäßabschnittes |
| US10867375B2 (en) | 2019-01-30 | 2020-12-15 | Siemens Healthcare Gmbh | Forecasting images for image processing |
| US11398026B2 (en) * | 2019-03-28 | 2022-07-26 | The Board Of Trustees Of The Leland Stanford Junior University | Systems and methods for synthetic medical image generation |
| EP3726461B1 (de) * | 2019-04-16 | 2021-10-27 | Siemens Healthcare GmbH | Verfahren und system zur erzeugung von synthetischen bildern mit schaltbaren bildkontrasten |
| DE102019207639A1 (de) | 2019-05-24 | 2020-11-26 | Siemens Healthcare Gmbh | Verbesserte Berechnung der Kontrastmittelkonzentration |
| EP3756547A1 (de) | 2019-06-28 | 2020-12-30 | Koninklijke Philips N.V. | Automatisierte koronarangiografieanalyse |
| US20210012486A1 (en) | 2019-07-09 | 2021-01-14 | Shenzhen Malong Technologies Co., Ltd. | Image synthesis with generative adversarial network |
| CN110391016B (zh) | 2019-07-10 | 2021-11-09 | 浙江大学 | 一种动态对比增强磁共振图像的分析方法 |
| EP4031893B1 (de) | 2019-09-18 | 2024-12-25 | Bayer Aktiengesellschaft | Erzeugung von mrt-aufnahmen der leber |
| JP7170897B2 (ja) | 2019-09-30 | 2022-11-14 | 富士フイルム株式会社 | 学習装置、方法およびプログラム、画像生成装置、方法およびプログラム、並びに画像生成モデル |
| EP3804615A1 (de) | 2019-10-08 | 2021-04-14 | Bayer AG | Erzeugung von mrt-aufnahmen der leber |
| CA3156921A1 (en) | 2019-10-08 | 2021-04-15 | Bayer Aktiengesellschaft | Generation of mri images of the liver without contrast enhancement |
| US20230120273A1 (en) | 2019-10-11 | 2023-04-20 | Bayer Aktiengesellschaft | Acceleration of mri examinations |
| EP3875979A1 (de) | 2020-03-06 | 2021-09-08 | Bayer Aktiengesellschaft | Optimiertes verfahren für dynamische kontrastverstärkende magnetresonanztomographie |
| EP4128261A1 (de) | 2020-04-03 | 2023-02-08 | Bayer Aktiengesellschaft | Erzeugen von radiologischen aufnahmen |
| US20210350935A1 (en) * | 2020-05-06 | 2021-11-11 | Quantitative Imaging Solutions, Llc | Therapeutic response prediction based on synthetic tumor models |
| US11308613B2 (en) | 2020-06-09 | 2022-04-19 | Siemens Healthcare Gmbh | Synthesis of contrast enhanced medical images |
| AU2021431204A1 (en) * | 2021-03-02 | 2023-08-31 | Bayer Aktiengesellschaft | System, method, and computer program product for contrast-enhanced radiology using machine learning |
| US11719778B1 (en) * | 2022-01-31 | 2023-08-08 | Regents Of The University Of Michigan | Multicontrast synthetic late gadolinium enhancement imaging using post-contrast magnetic resonance fingerprinting |
-
2021
- 2021-03-25 EP EP21713686.0A patent/EP4128261A1/de active Pending
- 2021-03-25 CA CA3177210A patent/CA3177210A1/en active Pending
- 2021-03-25 US US17/907,556 patent/US12394058B2/en active Active
- 2021-03-25 WO PCT/EP2021/057689 patent/WO2021197996A1/de not_active Ceased
- 2021-03-25 CN CN202180027276.7A patent/CN115398555A/zh active Pending
- 2021-03-25 JP JP2022559985A patent/JP7729836B2/ja active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CA3177210A1 (en) | 2021-10-07 |
| US12394058B2 (en) | 2025-08-19 |
| WO2021197996A1 (de) | 2021-10-07 |
| CN115398555A (zh) | 2022-11-25 |
| JP7729836B2 (ja) | 2025-08-26 |
| US20230147968A1 (en) | 2023-05-11 |
| JP2023521640A (ja) | 2023-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021197996A1 (de) | Erzeugen von radiologischen aufnahmen | |
| EP4031894B1 (de) | Vorhersage von mrt-aufnahmen durch ein mittels überwachten lernens trainiertes vorhersagemodell | |
| EP4041075B1 (de) | Erzeugung von mrt-aufnahmen der leber ohne kontrastverstärkung | |
| WO2022184297A1 (de) | Maschinelles lernen im bereich der kontrastmittelverstärkten radiologie | |
| EP4031893B1 (de) | Erzeugung von mrt-aufnahmen der leber | |
| EP4348573B1 (de) | Maschinelles lernen im bereich der kontrastmittelverstärkten radiologie | |
| EP4041057A1 (de) | Beschleunigung von mrt-untersuchungen | |
| EP3804615A1 (de) | Erzeugung von mrt-aufnahmen der leber | |
| EP4483197B1 (de) | Vorhersage einer repräsentation eines untersuchungsbereichs eines untersuchungsobjekts in einem zustand einer folge von zuständen | |
| EP4233726A1 (de) | Vorhersage einer repräsentation eines untersuchungsbereichs eines untersuchungsobjekts nach der applikation unterschiedlicher mengen eines kontrastmittels | |
| EP4143784B1 (de) | Maschinelles lernen im bereich der kontrastmittelverstärkten radiologie | |
| EP4581640A1 (de) | Erzeugen von synthetischen radiologischen aufnahmen | |
| DE102019217576A1 (de) | Erfassung einer Fehlausrichtung | |
| EP4336204A1 (de) | Beschleunigen von mrt-untersuchungen der leber | |
| EP4475137A1 (de) | Erzeugen von künstlichen kontrastverstärkten radiologischen aufnahmen | |
| WO2024046832A1 (de) | Erzeugen von synthetischen radiologischen aufnahmen | |
| WO2024251601A1 (de) | Erzeugen von künstlichen kontrastverstärkten radiologischen aufnahmen | |
| WO2024100234A1 (de) | Erzeugung von künstlichen kontrastmittelverstärkten radiologischen aufnahmen |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20221103 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20250918 |