Koninklijke Philips Corporation N.v.

U.S. Philips Corporation

Philips Intellectual Property & Standards Gmbh

Thomas Blaffert

Rafael Wiemker

Steffen Renisch

Cristian Lorenz

Thomas Buelow

Hans Barschdorf

Jens Von Berg

Zhiqiang Hu

Nicole Schadewaldt

Tobias Klinder

Heinrich Schulz

Sven Prevrhal

Bernd Schweizer

Juergen Weese

Daniel Bystrov

Michael Harald Kuhn

Vladimir Pekar

Thomas Leroy Laurence

Sven Kabus

Kirsten Regina Meetz

Jerome John Griesmer

Joerg Sabczynski

Astrid Ruth Franz

Sebastian Peter Michael Dries

Tom Brosch

Ingwer Curt Carlsen

Sharon Xiaorong Wang

Thorsten Manuel Buzug

Roland Johannes Opfer

Zuo Zhao

Martin Stahl

Nicholas C Dunand

Petrus J Schoenmakers

Sabine Dippel

A system and computer-implemented method are provided for annotation of image data. A user is enabled to iteratively annotate the image data. An iteration of said iterative annotation comprises generating labels for a current image data part based on user-verified labels of a previous image data part, and enabling the user to verify and correct said generated labels to obtain user-verified labels for the current image data part. The labels for the current image data part are generated by combining respective outputs of a label propagation algorithm and a machine-learned classifier trained on user-verified labels and image data and applied to image data of the current image data part. The machine-learned classifier is retrained using the user-verified labels and the image data of the current image data part to obtain a retrained machine-learned classifier.

Interactive iterative image annotation

The present disclosure relates to a method for controlling a magnetic resonance imaging guided radiation therapy apparatus comprising a magnetic resonance imaging system. The method comprises: acquiring magnetic resonance data using the magnetic resonance imaging system and the pulse sequence from an imaging volume; segmenting the magnetic resonance data into a plurality of segments indicating respective tissues in the imaging volume; creating a bulk electron density map of the imaging volume from the plurality of segments; displaying the bulk electron density map and radiation dose distributions for the plurality of segments on a graphical user interface, wherein the radiation dose distributions are determined using the bulk electron density map; receiving a modification signal for modifying at least a first segment of the segments; recreating the bulk electron density map using the modified first segment, and recalculating the radiation dose distribution using the bulk electron density map; redisplaying the bulk electron density map and the radiation dose distributions on the graphical user interface.

Radiotherapy planning with improve accuracy

The present invention teaches a method and system for computing an alternative electron density map of an examination volume. The processing system is configured to compute a first electron density map using a plurality of imaging data, compute a second electron density map, wherein the second electron density map is a simplified version of the first electron density map, and compute the alternative electron density map, using the first electron density map and the second electron density map.

Fall-back solution for uncertain regions in MRCAT images

An imaging method for identifying abnormal tissue in the lung is provided, comprising the recording of slice images of the lung by means of X-ray radiation, recording of blood vessels, differentiation of blood vessels and abnormal tissue, segmentation of the abnormal tissue and display of the segmented abnormal tissue on an output device. In addition, a computer tomograph for identifying abnormal tissue in the lung is provided, having a radiation source for recording slice images of the lung and blood vessels by means of X-ray radiation, a computer unit for differentiating the blood vessels from the abnormal tissue and for segmenting the abnormal tissue, as well as an output device for displaying the segmented abnormal tissue. Furthermore, a computer program is provided for controlling a computer tomograph for an identification of abnormal tissue in the lung by means of a radiation source, designed to record slice images of the lung and blood vessels by means of X-ray radiation, to differentiate the blood vessels from abnormal tissue, to segment the abnormal tissue and to control an output device for displaying the abnormal tissue.

Identifying abnormal tissue in images of computed tomography

An apparatus and a method for post processing 2D image slices (-) defining a 3D image volume. The apparatus comprises a graphical user interface controller (), a 2D segmenter () and a 3D segmenter (). The apparatus allows a user to effect calculation and display of a 2D segmentation of a cross section of an object shown in a slice () and calculation and display of a 3D segmentation of the object across the 3D image volume, the 3D segmentation based on the object's previously calculated 2D segmentation.

Workflow for ambiguity guided interactive segmentation of lung lobes

An apparatus for generating assignments between image regions of an image of an object and element classes includes an assigning unit () for assigning element classes to image regions of an element image of the object, which is indicative of a distribution of the element classes, depending on region and/or boundary features, which are determined depending on image values of a provided object image and provided first preliminary assignments. Thus, the resulting element image with the assignments to the element classes is not necessarily based on the provided object image only, but can also be based on the provided preliminary assignments. If the quality of the assignments defined by the element image would be restricted due to restrictions of the provided object image, these restrictions of the provided image can therefore be compensated by the preliminary assignments such that the quality of the resulting element image can be improved.

Apparatus for generating assignments between image regions of an image and element classes

The invention relates to an apparatus for generating an attenuation correction map. An image providing unit () provides an image of an object comprising different element classes and a segmentation unit () applies a segmentation to the image for generating a segmented image comprising image regions corresponding to the element classes. The segmentation is based on at least one of a watershed segmentation and a body contour segmentation based on a contiguous skin and fat layers in the image. A feature determination unit () determines features of at least one of a) the image regions and b) boundaries between the image regions depending on image values of the image and an assigning unit () assigns attenuation values to the image regions based on the determined features for generating the attenuation correction map. The performed image processing steps can allow for producing a high quality attenuation correction map, even if the initial image does not comprise image values related to the attenuation of radiation like a CT image.

Apparatus and method for generating an attenuation correction map

The invention relates to a rendering system () for rendering a view from an image dataset, the rendering system comprising a selecting unit () for selecting a subset of the image dataset, a computing unit () for computing a first principal axis of a tensor on the basis of the subset of the image dataset, and a rendering unit () for rendering the view on the basis of the first principal axis. Using the information about the directionality and orientation of a structure, comprised in the selected subset of the image dataset and extracted from the first principal axis of the tensor, the rendering system () is arranged to effectively assist the user in selecting an advantageous view from the image dataset.

Rendering a view from an image dataset

A system for displaying lung ventilation information, the system comprising an input () and a processing unit (). The input being provided for receiving multiple CT images () of a lung, each CT image () corresponding to one phase of at least two different phases in a respiratory cycle. The processing unit () being configured to compare CT images () corresponding to different phases in the respiratory cycle for determining a deformation vector field for each phase, to generate for each phase a ventilation image () based on the corresponding deformation vector field, to spatially align the ventilation images (), and to generate for at least one common position () in each one of the aligned ventilation images (), a function () of a time course of a ventilation value for said common position (), each ventilation value in the function () being based on the deformation vector fields corresponding to the aligned ventilation images ().

System for providing lung ventilation information

A nuclear imaging system includes a crystal identification system which receives a flood image which includes a plurality of peaks, each peak responsive to radiation detected by a corresponding scintillator crystal. A crystal identification processor partitions the flood image into a plurality of candidate regions with a watershed segmentator implementing a watershed algorithm. The candidate regions are linked in an adjacency graph, and then classified as background or relevant, where relevant regions contain a peak within the watershed lines. The regions are then assigned to a crystal according to an objective function and an assignability score. A calibration processor maps the peaks to a rectangular grid.

Automated crystal identification achieved via watershed segmentation

The present invention relates to an apparatus () for segmenting an object comprising sub-objects shown in an object image. The apparatus comprises a feature image generation unit () for generating a feature image showing features related to intermediate regions between the sub-objects and a segmentation unit () for segmenting the sub-objects by using the object image and the feature image. Preferentially, the feature image generation unit () is adapted for generating a feature image from the object image. In a further embodiment, the feature image generation unit () comprises a feature enhancing unit for enhancing features related to intermediate regions between the sub-objects in the object image.

Apparatus for segmenting an object comprising sub-objects

The invention relates to a system for adapting a plurality of model meshes to a plurality of image data. The system has a registration unit for registering the plurality of model meshes with the plurality of image data on the basis of a computation of a registration transformation for transforming the plurality of model meshes, and an adaptation unit for adapting the plurality of registered model meshes to the plurality of image data on the basis of a computation of locations of mesh vertices of the plurality of model meshes. The described system is capable of reducing motion artifacts in tomographic images computed from data acquired at a plurality of different cardiac cycle phases.

Reduction of heart motion artifacts in thoracic CT imaging

A potential region of interest segmentation device segments an image data into regions of potential interest. From the regions of potential interest, an identifying device identifies a region of interest including an object of interest based on a set of rules. A recognizing device differentiates among the identified objects of interest and selects at least one particular object of interest.

Hot spot detection, segmentation and identification in pet and spect images

A system () an image acquisition device, an image workstation, computer-readable medium and method for visualizing an anatomical tree structure is disclosed. The anatomical tree structure is segmented from a three-dimensional image set of at least a portion of a body. A planar angular visualization of the anatomical tree structure is then determined. The planar angular visualization of the anatomical tree structure is then displayed. Since the displayed anatomical tree structure has no occlusions or intersections of segments, the anatomical tree is much easier to read which facilitates subsequent automated or manual diagnosis of the tree for anomalies.

Growing community of inventors

Hamburg, Germany

Thomas Blaffert