Koninklijke Philips Corporation N.v.

Yogish Mallya

Lyubomir Georgiev Zagorchev

Narayanan Ayyakad Krishnan

Manish Sharma

Daniel Bystrov

Heinrich Schulz

Prashant Kumar

Timothy Poston

Nicole Schadewaldt

Shekhar Dwivedi

Torbjoern Vik

Narayan Ayyakad Krishnan

Shivakumar Kunigal Ramaswamy

Vidya Madapusi Srinivas Prasad

The invention relates to a processing system and corresponding method for processing image data and for indexing regions of interest in an object of interest. The system comprises a registration unit for registering the image data, a sub-volume generator generating sub-volumes from the image data, a composite image generator for generating multiple sets of composite images from each sub-volume, each set of composite images representing a different projection. The system comprises an indexing unit for generating indexed regions of interest in each sub-volume by assessing each of the set of composite images in parallel and a combining unit for combining each set of composite images of each sub-volume into a scan level prioritization.

Automated system for rapid detection and indexing of critical regions in non-contrast head CT

Interactive mesh deformation for in-plane 3D segmentation/delineation for radiation therapy planning done on a slice by slice basis of a region/a volume of interest (VOI, ROI). Segmentation starts by some automatic 3D algorithm approximating the organ surface roughly by some triangular surface mesh which mesh is afterwards manually refined by the user who deforms it to bring it closer to the region of interest. The deformation is an invertible, i.e. one-to-one, mapping avoiding self-intersections of the deformed mesh thereby preserving the topology of the anatomy. The deformation mapping involves a Gaussian function (Gaussian deformation kernel) restricting the deformation to a local region. The user picks with the pointer a start point on a selected image slice through the volume and moves it to some end point. The distance the mesh vertices move decreases exponentially with the distance to the start point. Additionally, surface mesh resolution is increased by iteratively subdividing mesh triangles in the vicinity of a user-selected contour in a surface mesh until every pixel or voxel contains at least one triangle vertex.

In-plane and interactive surface mesh adaptation

A method includes obtaining first volumetric image data, which is acquired at a first time, including a region of interest with a structural feature located at a first position. The method further includes obtaining second volumetric image data, which is acquired at a second different time, including the region of interest with the structural feature located at a second different position. The method further includes determining a registration transformation that registers the first and second volumetric image data such that the at least one structural feature in the first volumetric image data aligns with the at least one structural feature in the second volumetric image data. The registration transformation is based at least on a contour guided deformation registration. The method further includes generating a signal indicative of the registration transformation.

Contour guided deformable image registration

A system for processing multi-subject volumes comprises a volume input () for receiving an input volume image dataset () comprising a plurality of subjects scanned simultaneously. A metadata input () receives metadata () relating to individual ones of the subjects. A subject finder () identifies a plurality of portions of the input volume image dataset (), each portion comprising one of the subjects. A volume image dataset generator () generates a plurality of separate volume image datasets (), each separate volume image dataset () comprising one of the portions of the input volume image dataset. A metadata handler () associates the metadata () relating to a subject with the separate volume image dataset () comprising the portion comprising the subject.

Data processing of group imaging studies

A method for cardiac imaging for determining a myocardial region of interest (ROI) is disclosed. The method includes acquiring functional imaging data of a subject, where the functional imaging data includes at least the myocardium. A ROI encompassing at most the myocardium from the acquired functional imaging data, and diagnostic parameters relating to the myocardium are estimated and quantified based on the determined ROI. In one embodiment, the ROI is determined from a projection image representation utilizing histogram based thresholding and ray casting based localization to determine the extents of the ROI. In another embodiment, the ROI is determined from a volumetric image representation utilizing clustering Manhattan distance based cleaning to determine cardiac angles used for reorienting the left ventricle.

Region of interest definition in cardiac imaging

An angiographic image processing system includes a filtering module () configured to filter an angiographic image based on blood vessel diameter () to identify neovasculature having small blood vessel diameter, and a display sub-system () configured to display the angiographic image with the identified neovasculature. A neovasculature density computation module () is configured to compute density of the neovasculature identified by the filtering module ().

Growing community of inventors

Bengaluru, India

Yogish Mallya