Koninklijke Philips Corporation N.v.

Martin Bergtholdt

Rafael Wiemker

Thomas Buelow

Tobias Klinder

Julien Senegas

Kirsten Regina Meetz

Jochen Peters

Lyubomir Georgiev Zagorchev

Fabian Wenzel

Carsten Meyer

Cristian Lorenz

Thomas Netsch

Axel Saalbach

Thomas Heiko Stehle

Ingwer-Curt Carlsen

Irina Waechter-Stehle

Peter Mazurkewitz

Alexander Schmidt-Richberg

Lina Arbash Meinel

Daniel Bystrov

Hanns-Ingo Maack

Heinrich Schulz

Hubert Cecile Francois Martens

Peter Koken

Klaus Erhard

Joerg Sabczynski

Rolf Jürgen Weese

Harald Sepp Heese

Kongkuo Lu

Sheng Xu

Bernd Menser

Andre Goossen

Frank Olaf Thiele

Johannes Buurman

Gerrit-jan Bloem

Sven Kroenke

Johan Gerard Kleibeuker

Sascha Andreas Jockel

Johannes Cornelis Koudijs

Dominik Berjamin Kutra

Jeffrey Miller

Houchun Hu

Fabien Wenzel

An X-ray imaging system () includes an X-ray source (), an X-ray detector (), a depth camera (), and a processor (). The processor () receives depth camera image data from the depth camera, projects the depth camera image data onto a radiation-receiving surface of the X-ray detector (), from a perspective of the X-ray source (), and generates an image representation () of the projected depth camera image data on the radiation-receiving surface of the X-ray detector (), from a perspective of the depth camera ().

Positioning an object with respect to an X-ray detector

A cortical malformation identification method includes quantitatively evaluating, using a processor of a computer that includes the processor and a memory, digital image data from a magnetic resonance imaging (MRI) scan on a cerebral cortex to produce quantified scan data. The method also includes automatically detecting a cortical malformation based on the quantified scan data. An image of the cerebral cortex may be color-coded so that the cortical malformation is shown in a different color than the remainder of the cerebral cortex in the image, based on the quantified scan data. Additionally or alternatively, a 3-dimensional representation of the cerebral cortex may be mapped to the quantified scan data to produce a mapped image of the cerebral cortex including the detected cortical malformation.

Cortical malformation identification

The invention provides for a medical apparatus () comprising a subject support () configured for moving a subject () from a first position () to a second position () along a linear path (). The subject support comprises a support surface () for receiving the subject. The subject support is further configured for positioning the subject support in at least one intermediate position (). The subject support is configured for measuring a displacement () along the linear path between the first position and the at least one intermediate position. Each of the at least one intermediate position is located between the first position and the second position. The medical apparatus further comprises a camera () configured for imaging the support surface in the first position. Execution of machine executable instructionscause the a processor () controlling the medical apparatus to: acquire () an initial image () with the camera when the subject support is in the first position; control () the subject support to move the subject support from the first position to the second position; acquire () at least one intermediate image () with the camera and the displacement for each of the at least one intermediate image as the subject support is moved from the first position to the second position; and calculate () a height profile () of the subject by comparing the initial image and the at least one intermediate image. The height profile is at least partially calculated using the displacement. The height profile is descriptive of the spatially dependent height of the subject above the support surface.

Determination of a subject profile with a camera

There is provided a computer implemented method () for medical image processing. The method comprises providing () a database of medical images and providing () an initial machine learning model which is trained for segmenting or classifying a medical feature in the medical images. The method also comprises extracting () a subset of medical images from the database based on a similarity score of the medical images and training () the machine learning model using the extracted subset of medical images in order to provide a refined machine learning model.

Computer-implemented method to increase the accuracy of machine learning models for medical image processing

The present invention relates to an X-ray radiograph apparatus (). It is described to placing () an X-ray source () relative to an X-ray detector () to form an examination region for the accommodation of an object, wherein, a reference spatial coordinate system is defined on the basis of geometry parameters of the X-ray radiography apparatus. A camera () is located () at a position and orientation to view the examination region. A depth image of the object is acquired () with the camera within a camera spatial coordinate system, wherein within the depth image pixel values represent distances for corresponding pixels. A processing unit () transforms (), using a mapping function, the depth image of the object within the camera spatial coordinate system to the reference spatial coordinate system, wherein, the camera position and orientation have been calibrated with respect to the reference spatial coordinate system to yield the mapping function that maps a spatial point within the camera spatial coordinate system to a corresponding spatial point in the reference spatial coordinate system. A synthetic image is generated () within the reference spatial coordinate system. The synthetic image is output () with an output unit ().

X-ray radiography apparatus

The appropriate positioning of a patient in an X-Ray imaging system can present difficulties for medical professional owing, on one hand to the small size of important anatomical aspects which need to be captured in X-Ray images, and on the other hand to the significant movements in a field of view presented by a typical patient. The present application proposes to obtain an image of the position of a patient in the field of view at approximately the same time that an initial X-Ray image is obtained. If it proves necessary to obtain a subsequent X-Ray image with updated field of view settings (for example, collimation parameters), the movement of the patient at the point of taking the second image is factored into the provision of updated field of view settings.

Field of view adjustment

A method and apparatus for segmenting a two-dimensional image of an anatomical structure includes acquiring () a three-dimensional model of the anatomical structure. The three-dimensional model includes a plurality of segments. The acquired three-dimensional model is adapted to align the acquired three-dimensional model with the two-dimensional image (). The two-dimensional image is segmented by the plurality of segments of the adapted three-dimensional model.

Method and apparatus for segmenting a two-dimensional image of an anatomical structure

The invention provides for a medical instrument () comprising a processor () and a memory () containing machine executable instructions (). Execution of the machine executable instructions causes the processor to: receive () a first magnetic resonance image data set () descriptive of a first region of interest () of a subject () and receive () at least one second magnetic resonance image data set (') descriptive of a second region of interest () of the subject. The first region of interest at least partially comprises the second region of interest. Execution of the machine executable instructions further cause the processor to receive () an analysis region () within both the first region of interest and within the second region of interest. Execution of the machine executable instructions further cause the processor to construct () a cost function comprising an intra-scan homogeneity measure separately for the first magnetic resonance image data set and separately for each of the at least one second magnetic resonance image data set. The cost function further comprises an inter-scan similarity measure calculated using both the first magnetic resonance image data set and each of the at least one second magnetic resonance image data set. Execution of the machine executable instructions further cause the processor to by performing an optimization () of the cost function by calculating a first intensity correction map () for the first magnetic resonance image data set using an intensity correction algorithm within the analysis region and at least one second intensity correction map () for each of the at least one second magnetic resonance image data set within the analysis region. Execution of the machine executable instructions further cause the processor to calculate () a first corrected magnetic resonance image () descriptive of the analysis region using the first magnetic resonance image data set and the first intensity correction map. Execution of the machine executable instructions further cause the processor to calculate () at least one second corrected magnetic resonance image () descriptive of the analysis region using the at least at least one second magnetic resonance image data set and the at least one second intensity correction map.

Intensity corrected magnetic resonance images

A planning tool, system and method include a processor () and memory () coupled to the processor which stores a planning module (). A user interface () is coupled to the processor and configured to permit a user to select a path through a pathway system (). The planning module is configured to upload one or more slices of an image volume () corresponding to a user-controlled cursor point () guided using the user interface such that as the path is navigated the one or more slices are updated in accordance with a depth of the cursor point in the path.

Automatic depth scrolling and orientation adjustment for semi-automated path planning

The present invention relates to medical image editing. In order to facilitate the medical image editing process, a medical image editing device () is provided that comprises a processor unit (), an output unit (), and an interface unit (). The processor unit () is configured to provide a 3D surface model of an anatomical structure of an object of interest. The 3D surface model comprises a plurality of surface sub-portions. The surface sub-portions each comprise a number of vertices, and each vertex is assigned by a ranking value. The processor unit () is further configured to identify at least one vertex of vertices adjacent to the determined point of interest as an intended vertex. The identification is based on a function of a detected proximity distance to the point of interest and the assigned ranking value. The output unit () is configured to provide a visual presentation of the 3D surface model. The interface unit () is configured to determine a point of interest in the visual presentation of the 3D surface model by interaction of a user. The interface unitis further configured to modify the 3D surface model by displacing the intended vertex by manual user interaction. In an example, the output unit () is a display configured to display the 3D surface model directly to the user ().

Medical image editing

A method for processing image data includes obtaining a first set of 3D volumetric image data. The 3D volumetric image data includes a volume of voxels. Each voxel has an intensity. The method further includes obtaining a local voxel noise estimate for each of the voxels of the volume. The method further includes processing the volume of voxels based at least on the intensity of the voxels and the local voxel noise estimates of the voxels. An image data processor () includes a computer processor that at least one of: generate a 2D direct volume rendering from first 3D volumetric image data based on voxel intensity and individual local voxel noise estimates of the first 3D volumetric image data, or registers second 3D volumetric image data and first 3D volumetric image data based at least one individual local voxel noise estimates of second and first 3D volumetric image data sets.

Image data processing

A system and method are provided for brain tissue classification, which involves applying an automated tissue classification technique to an image of a brain based on a prior probability map, thereby obtaining a tissue classification map of the brain. A user is enabled to, using a user interaction subsystem, provide user feedback which is indicative of a) an area of misclassification in the tissue classification map and b) a correction of the misclassification. The prior probability map is then adjusted based on the user feedback to obtain an adjusted prior probability map, and the automated tissue classification technique is re-applied to the image based on the adjusted prior probability map. An advantage over a direct correction of the tissue classification map may be that the user does not need to indicate the area of misclassification or the correction of the misclassification with a highest degree of accuracy. Rather, it may suffice to provide an approximate indication thereof.

Brain tissue classification

Image processing method or apparatus (IP) to transform a 3D image data set (DS) into a visually protected one (DSX). The 3D image set includes an object region (OR) and a background region (BR) that defines s silhouette of an imaged object (P). An inadvertent or malicious direct volume rendering of the silhouette (IF) of the object is prevented by applying a randomization operation to at least the background region (BR).

Visual anonymization of medical datasets against 3D volume rendering

A system and method are provided for interactive editing of a mesh which has been applied to a three-dimensional (3D) image to segment an anatomical structure shown therein. To facilitate the interactive editing of the applied mesh, a view of the 3D image is generated which shows a mesh part to be edited, with the view being established based on a local orientation of the mesh part. Advantageously, the view may be generated to be substantially orthogonally to the mesh part, or to a centerline of the anatomical structure which is determined as a function of the mesh part. Accordingly, an orthogonal view is established which facilitates the user in carrying out the editing action with respect to the mesh part. It is therefore not needed for the user to manually navigate through the 3D image to obtain a view which is suitable for mesh editing, which is typically time consuming.

Interactive mesh editing

The present invention provides for means for linking breast lesion locations across imaging studies. In particular, a generic three-dimensional representation of the female breast is used. Automatic translation of the lesion location into standard clinical terminology and aligning the breast model with individual patient images is comprised. Moreover, a mechanism for linking image locations showing a lesion to a location in the breast model is presented. If desired, a region of interest can be calculated by a region of interest definition module that predicts a region of interest of a known lesion in terms of the breast model representation in a new imaging study.

Growing community of inventors

Hamburg, Germany

Martin Bergtholdt