Siemens Medical Solutions Usa, Inc.

Optellum Limited

Siemens Corporation

Siemens Aktiengesellschaft

Siemens Healthcare Gmbh

Technische Universitat Munchen

Jerome Declerck

Timor Kadir

Matthew David Kelly

Carlos Federico Arteta Montilva

Jingdan Zhang

Nicholas Dowson

Dorin Comaniciu

Shaohua Kevin Zhou

Ali Kamen

Tommaso Mansi

Michal Sofka

Neil Birkbeck

Thomas Boettger

Jens Wetzl

Thomas George Wright

Kinda Anna Saddi

Jens Kaftan

Kevin Scott Hakl

Vaclav Potesil

Bernhard Fuerst

Timo Kohlberger

Lyndsey Pickup

Francois Carnis

Vaclav Potesill

A CADx system for analysing medical images to monitor at least one feature on the image to predict at least one of a change of the state or maintenance of the current state of a monitored feature within a time frame is described. The system comprising: an input circuit for receiving at least one medical input image; a feature state change circuit for analysing the received input image and predicting a state change comprising: a state change predictor to predict a state change of the monitored feature within the time frame; and an output circuit to output an indication of the change of state or maintenance of the current state of the monitored feature within the time frame based on the prediction of the feature state change predictor. A method of training a feature state change prediction circuit using Machine Learning is also described.

Method and apparatus to predict feature state change within an image

A method for providing a lung disease risk measure in a Computer Aided Diagnosis system is described. The method comprises the steps of: receiving an input comprising at least one input image showing all or part of the lungs of a patient; analysing the input to identify a feature descriptor comprised of at least one feature group, where each feature group comprises at least one feature computed from the input image; calculating a score explanation factor for each feature group, and an overall disease risk score for the patient's risk of lung disease from the feature descriptor; outputting the overall disease score risk score and a corresponding score explanation factor for each feature group. A computer aided diagnosis system is also described, along with a method for training a computer aided diagnosis system.

CAD device and method for analysing medical images

A method for providing a lung disease risk measure in a Computer Aided Diagnosis system is described. The method comprising the steps of: receiving a plurality of inputs for a subject, each input comprising at least one image showing all or part of the lungs of a patient and a time stamp for the image, where the inputs are obtained at varying intervals; analysing the inputs to assess temporal changes in the images using at least one of an input data encoder and a time stamp encoder; inputting the output of at least one of the encoders to a score calculator to calculate a risk score; outputting the risk score indicating the lung disease risk for the subject. A Computer Aided diagnosis system for implementing the method is also described.

Using unstructured temporal medical data for disease prediction

A Computer Aided Diagnosis, CADx, system () is described that comprises: at least one input () configured to provide at least one input medical image; and a CADx processing engine () configured to receive and process the at least one input medical image and produce at least one CADx score. A CADx score mapping circuit is operably coupled to the CADx processing engine () and configured to: map the at least one CADx score to a risk adjusted virtual score; and generate an output () of at least the risk adjusted virtual score associated with the processed at least one input medical image. The at least one CADx score and the risk adjusted virtual score correspond to an equivalent risk of condition or disease associated with a patient.

System, method and apparatus for assisting a determination of medical images

A quantification system () is described that includes: at least one input () configured to provide two input medical images and two locations of interest in said input medical images that correspond to a same anatomical region; and a mapping circuit () configured to compute a direct quantification of change of said input medical images from the at least one input ().

A quantification system () is described that includes: at least one input () configured to provide at least one input medical image and provide a location of interest in the at least one input medical image; and a mapping circuit (). The mapping circuit () is configured to: compute a direct quantification result from the location of interest of the at least one input medical image to a quantification of interest and output a direct first quantification result therefrom; generate a saliency map as part of the computation of the direct quantification result; and derive a segmentation from the saliency map, such that the segmentation independently generates a second quantification result that is within a result range of the direct first quantification result.

A voice controlled system uses context-sensitive interpretation of voice comments received by a voice recognition system to identify a region of patient image data identified by a verbal comment.

Context-sensitive identification of regions of interest in a medical image

A method and system for prediction of respiratory motion from 3D thoracic images is disclosed. A patient-specific anatomical model of the respiratory system is generated from 3D thoracic images of a patient. The patient-specific anatomical model of the respiratory system is deformed using a biomechanical model. The biomechanical model is personalized for the patient by estimating a patient-specific thoracic pressure force field to drive the biomechanical model. Respiratory motion of the patient is predicted using the personalized biomechanical model driven by the patient-specific thoracic pressure force field.

System and method for prediction of respiratory motion from 3D thoracic images

In a method for localizing a candidate foci in neuroimaging, two images are acquired, one being a baseline (interictal) image and another being an intervention (ictal) image. The two images are aligned and the intensities of the images are normalized. A difference image is calculated by subtracting the baseline (interictal) image from the intervention (ictal) image. The difference image is normalized and regions of interest are selected as candidate foci.

Method for localization of an epileptic focus in neuroimaging

A method and system for automatic multi-organ segmentation in a 3D image, such as a 3D computed tomography (CT) volume using learning-base segmentation and level set optimization is disclosed. A plurality of meshes are segmented in a 3D medical image, each mesh corresponding to one of a plurality of organs. A level set in initialized by converting each of the plurality of meshes to a respective signed distance map. The level set optimized by refining the signed distance map corresponding to each one of the plurality of organs to minimize an energy function.

Method and system for multi-organ segmentation using learning-based segmentation and level set optimization

In a method and apparatus for calibrating image data from a given medical imaging protocol, reference image data is obtained from a scan of a reference object using the medical imaging protocol, and the obtained reference image data of the reference object is compared to standard reference image data for the reference object. The obtained reference image data is then modified to reduce an error between the obtained reference image data and the standard reference image data. Subject image data id then obtained from a scan of a subject using the medical imaging protocol, and modified based on the modified reference image data. A value of a variable is obtained from the modified subject image data, for display with unmodified subject image data.

Method and apparatus for calibrating medical image data

In a method and apparatus for analyzing medical imaging data of a subject from an imaging modality using a tracer, data from detection of tracer emission events at least one region of a scanned imaging volume are obtained, and the data processed to establish sub-periods or time points within a scan period for the emission events. A rate of change of emission events per unit time for a given region is then calculated, for example by obtaining a number of emission events in each sub-period in the given region, and fitting a line through the values for the sub-periods.

Methods and apparatus for analyzing medical imaging data

In methods and an apparatus for analyzing a selected region of interest in medical image data of a subject, an initial image data set is obtained, and the initial image data set is filtered to generate a filtered data set. The filtering includes computing, for each voxel of the initial image data set, a value of intensity for a standardized volume of interest centered on that voxel. A user selection of a region of interest in the initial image data set is registered, and from the filtered image data set a value of intensity for the selected region of interest is computed.

Methods of analyzing a selected region of interest in medical image data

An image processing method is described that allows a user to deform an overlay image for the purpose of registration with a source image. The user defines a stretch vector for example by 'clicking and dragging' a mouse pointer and an algorithm deforms the overlay image according to a linear interpolated roll-off function.

Interactive manual deformable registration of images

A method is described for acquiring and analysing the data produced by Positron Emission Tomography (PET), which method provides for an accurate estimation of vascular compartment volume, V. An MRI scan and the PET scan is performed simultaneously and the results of the former is used to derive a value for V. The value so derived is then used in pharmacokinetic modelling along with the results of the functional scan.

Growing community of inventors

Oxford, United Kingdom

Jerome Declerck