Ge Precision Healthcare LLC

Safran

Safran Aircraft Engines

Vincent Jerome Morard

Nicolas Gogin

Estelle Parra

Jorge Hernandez Londono

David Tourais

Jerome F Knoplioch

Julien Schneider

Yann Le Guilloux

Adele Courot

Benoît Vincent Pierre Lasjaunias

Nicolas Coustaud

Ronan Quelever

Luc Nicodeme

Laura Dumont

Lionel Christian Jean-Loic Gay

Various methods and systems are provided for image data segmentation. In one example, a method includes receiving a first segmentation input selecting a first set of pixels of a two-dimensional (2D) projected rendering, the 2D projected rendering generated from a 3D medical image dataset, retropropagating the selected first set of pixels to 3D space based on a mapping between the 2D projected rendering and the 3D medical image dataset to form a 3D segmentation mask, and saving the 3D segmentation mask in memory and/or applying the 3D segmentation mask to the 3D medical image dataset, wherein the 2D projected rendering is an intensity projection rendering.

3D interactive annotation using projected views

Techniques are described that facilitate interactive segmentation of medical images with low latency in a cloud-based medical imaging application. According to an embodiment, a system is provided that comprises a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory. The computer executable components comprise a reception component that receives a compressed representation of a three-dimensional (3D) medical image generated from the 3D medical image by an encoder network of a deep neural network model comprising an encoder network and a decoder network, an interaction component that receives user input relative to a displayed portion of the 3D medical image indicating an object included in the displayed portion for segmentation, and a segmentation component that generates a segmentation mask for the object based on the user input using the compressed representation and the decoder network.

Low latency interactive segmentation of medical images within a web-based deployment architecture

Presently disclosed are systems and methods for extrapolating a predictive two-dimensional (2D) segmentation to indicate a predicted region of interest (ROI) in a 2D medical image frame rendered from a set of three-dimensional (3D) medical scan data, wherein the predictive segmentation is based on a user-defined 2D segmentation that annotates the ROI in another image frame rendered from the 3D medical scan data. Present embodiments can utilize a user-defined or user-modified 2D segmentation of a frame to extrapolate predicted 2D segmentations for all of the other frames within a set of 3D medical scan data. This enables present embodiments to effectively annotate the ROI in a series of 2D medical image frames with minimal input from a clinician, reducing the amount of time the clinician spends analyzing the 3D medical scan data.

Methods for interactive annotation of medical images in a client-server architecture

Various methods and systems are provided for real-time image segmentation of medical image data. In one example, the real-time image segmentation of the medical image data may include updating an initial segmentation of the medical image data in real-time. The update may be based on a user input to a regularization brush applied to the medical image data, the user input to the regularization brush allowing modification of a volume of the initial segmentation.

Methods and systems for real-time image 3D segmentation regularization

A 3D segmentation editing system accurately updates the segmentations of non-edited images of a 3D scan to reflect segmentation edits applied to other images of the scan using localized interpolation. In one or more embodiments, rather than replacing the entireties of the initial segmentations of non-edited images with newly generated, globally interpolated segmentations, the segmentation editing system applies a distance-based criterion to the interpolation of segmentation edits, such that only portions of the segmentations of the non-edited images that correspond to areas that were manually annotated in the edited images will be modified by the interpolation process, and the initial segmentations will be maintained outside of those edited areas. In this way, the system merges the interpolated segmentation with the initial segmentation for each non-edited image in a manner that mitigates unreliable modifications to the initial segmentations in areas far from the edited areas.

Interactive 3D annotation tool with slice interpolation

Various methods and systems are provided for determining and characterizing features of an anatomical structure from a medical image. In one example, a method comprises acquiring a plurality of medical images over time during an exam, registering the segmented anatomical structure between the plurality of medical images, segmenting an anatomical structure in a one of the plurality of medical images after registering the plurality of medical images, creating and characterizing a reference region of interest (ROI) in each of the plurality of medical images, determining characteristics of the anatomical structure by tracking pixel values of the segmented and registered anatomical structure over time, and outputting the determined characteristics on a display device.

Methods and systems for characterizing anatomical features in medical images

A method of non-destructive checking of a component for aeronautics, the method including the following steps of acquiring a volume by tomographic imaging, of generating by computer simulation a surface corresponding to the component to be analyzed, of registering the volume and the surface by optimizing a similarity criterion defined by a function taking into account the correlation between normal vectors of a field of normal vectors of the surface displaced by transformation and a gradient of a gradient field of the volume, the optimization being performed as a function of transformations for determining the optimal transformation which maximizes the similarity criterion, of storing the optimal transformation, of establishing the correspondence between the surface and the volume obtained with the aid of the optimal transformation.

Method of non-destructive checking of a component for aeronautics

A method of non-destructive testing of an aeronautical component, including a righting processing including Generation of a median surface of the component extracted from a tomographic volume, the median surface dividing the component into two parts, Determination of a field of normal vectors normal to the median surface, Flattening of the median surface to form a flattened median surface in a plane, Reconstruction of a righted volume containing the component righted about the flattened median surface, the reconstruction being performed by mapping between voxels of the righted volume along directions orthogonal to the flattened median surface and between voxels of the volume along the normal vectors of the median surface which are associated with these respective orthogonal directions, Analysis of the righted volume thus obtained so as to identify the anomalies of the component.

Method of non-destructive testing by righting

The method of estimating a quality index of a gray-scale encoded three-dimensional image of a composite material part includes an obtaining step for obtaining a histogram from the image, the histogram representing for each class of a plurality of classes each including at least one gray-scale level, the number of voxels of the image having a gray-scale level belonging to the class; an extraction step for extracting a predetermined number of Gaussian functions present in the histogram; and an estimation step for estimating at least one quality index of the image from parameters characterizing the Gaussian functions extracted from the histogram.

Method and a device for estimating a quality index for a 3D image of a composite material part

A method of characterizing a part made of woven composite material, includes calculating autocorrelation values of a three-dimensional image in an observation window of the volume of the part for a plurality of spatial vectors used as the autocorrelation interval, and then detecting at least one local extremum in the autocorrelation value on a main orientation of the weaving in order to determine a mean in the observation window for the distance between neighboring parallel yarns.

Method for characterizing a part made of a woven composite material

Method and system for non-intrusive measurement of volume density of a specific phase in a part, comprising: processor producing a volume image of the part, the image being formed by a three-dimensional grid of voxels, the values of which indicate the disposition of the specific phase in the part, processor associating a binary coefficient with each voxel of the volume image, thus constructing an initial three-dimensional matrix representation of binary coefficients representing a presence or absence of the specific phase in zones of the part corresponding to the voxels, processor convoluting the initial matrix representation with a convolution matrix kernel corresponding to a predetermined reference volume, the convolution performed by effecting a composition of three (successive) monodimensional convolutions in three independent directions, thus forming a resultant matrix representation, each resultant coefficient of which represents a volume ratio (the density) of the specific phase in the reference volume.

Growing community of inventors

Versailles, France

Vincent Jerome Morard