Siemens Medical Solutions Usa, Inc.

Siemens Corporate Research, Inc.

Siemens Aktiengesellschaft

Mikael Rousson

Nikolaos Paragios

Daniel Cremers

Visvanathan Ramesh

Chenyang Xu

Shmuel Aharon

Oliver Fluck

Frank Sauer

Ali Khamene

Charles Henri Florin

Kinda Anna Saddi

Juan Carlos Celi

Nikolaos Paraglos

Jerome Piovano

Ying Bai

Barbara Ofstad

Christian Schaller

A method for automatically segmenting a liver in digital medical images includes providing a 3-dimensional (3D) digital image I and a set of N training shapes {&#x3c6;}for a liver trained from a set of manually segmented images, selecting a seed point to initialize the segmentation, representing a level set function &#x3c6;(&#x3b8;x+h) of a liver boundary &#x393; in the image as is a mean shape, {V(x)}are eigenmodes where n&#x3c;N, &#x3b1;are shape parameters, and h &#x3b5; Rand &#x3b8; &#x3b5; [0,2&#x3c0;]are translation and rotation parameters that align the training shapes, minimizing a first energy functional to determine the shape, translation, and rotation parameters to determine a shape template for the liver segmentation, defining a second energy functional of the shape template and a registration mapping weighted by image intensity histogram functions inside and outside the boundary, and minimizing the second energy functional to determine the registration mapping, where the registration mapping recovers local deformations of the liver.

System and method for global-to-local shape matching for automatic liver segmentation in medical imaging

A fast and robust segmentation model for piecewise smooth images is provided. Local statistics in an energy formulation are provided as a functional. The shape gradient of this new functional gives a contour evolution controlled by local averaging of image intensities inside and outside the contour. Fast computation is realized by expressing terms as the result of convolutions implemented via recursive filters. Results are similar to the general Mumford-Shah model but realized faster without having to solve a Poisson partial differential equation at each iteration. Examples are provided. A system to implement segmentation methods is also provided.

Efficient segmentation of piecewise smooth images

A method for histogram calculation using a graphics processing unit (GPU), comprises storing image data in a two-dimensional (2D) texture domain; subdividing the domain into independent regions or tiles; calculating in parallel, in a GPU, a plurality of tile histograms, one for each tile; and summing up in parallel, in the GPU, the tile histograms so as to derive a final image histogram.

Method and system for histogram calculation using a graphics processing unit

A general framework to enhance performance of automatic segmentation of a plurality of structures in medical imaging applications incorporates inter-structure spatial dependencies in to existing segmentation algorithms. Ranking the structures according to their dependencies allows a hierarchical approach to automatically segmenting multiple structures that improves each individual segmentation and provides automatic initializations.

General framework for image segmentation using ordered spatial dependency

Methods and systems for image segmentation are disclosed. A nonlinear statistical shape model of an image is integrated with a non-parametric intensity model to estimate characteristics of an image and create segmentations of an image based on Bayesian inference from characteristics of prior learned images based on the same models.

Efficient kernel density estimation of shape and intensity priors for level set segmentation

A segmentation of the esophagus from image data by specifying only the two end points is disclosed. Surrounding structures are used as high-level constraints to construct shape and appearance models. Prior shape information is integrated for the segmentation of a new esophagus using a Bayesian formulation. This permits to automatically select the proper models. Given the end points, a shortest path algorithm provides the optimal esophagus according to the Bayesian formulation.

Probabilistic minimal path for automated esophagus segmentation

A method for segmentation of an image interactively with a user utilizes level set segmentation and includes selecting by user input respective areas of object and of background; initializing an embedding function implementing a segmentation boundary according to the selecting; computing intensity distributions and for the respective areas of object and of background; and performing repeatedly the steps below until convergence is reached: (a) evolving the embedding function, (b) recomputing the intensity distributions, and (c) checking for new user input and, if so: (d) updating labeling of the areas of object and background.

Method and system for interactive image segmentation

A method for four-dimensional (4D) image verification in respiratory gated radiation therapy, includes: acquiring 4D computed tomography (CT) images, each of the 4D CT images representing a breathing phase of a patient and tagged with a corresponding time point of a first surrogate signal; acquiring fluoroscopic images of the patient under free breathing, each of the fluoroscopic images tagged with a corresponding time point of a second surrogate signal; generating digitally reconstructed radiographs (DRRs) for each breathing phase represented by the 4D CT images; generating a similarity matrix to assess a degree of resemblance in a region of interest between the DRRs and the fluoroscopic images; computing a compounded similarity matrix by averaging values of the similarity matrix across different time points of the breathing phase during a breathing period of the patient; determining an optimal time point synchronization between the DRRs and the fluoroscopic images by using the compounded similarity matrix; and acquiring a third surrogate signal and turning a treatment beam on or off according to the optimal time point synchronization.

Four-dimensional (4D) image verification in respiratory gated radiation therapy

This invention relates to shape priors for level set representations. An embodiment of the invention comprises a first stage and a second stage. In the first stage, a shape model can be built directly on level set space using a collection of samples. The shape model can be constructed using a variational framework to create a non-stationary pixel-wise model that accounts for shape variabilities. Then, in the second stage, the shape model can be used as basis to introduce the shape prior in an energetic form. In terms of level set representations, the shape prior aims at minimizing non-stationary distance between the evolving interface and the shape model. An embodiment according to the present invention can be integrated with an existing, data-driven variational method to perform image segmentation for physically corrupted and incomplete data.

Shape priors for level set representations

A system and method for non-rigid image registration using distance functions includes portions for receiving a source shape into an image space, integrating a global linear registration model with local deformations to assess the source shape, optimizing a functional defined on a parameter or feature space where the functional quantifies the similarity between the source shape and a target shape in terms of distance functions, creating an augmented registration space including a plurality of target shape clones coherently positioned in the image space, tracking moving interfaces between the source shape and the target shapes and clones through a level set method, and registering the source shape by seeking mutual correspondences between the source shape, the target shape and the target shape clones.

Non-rigid image registration using distance functions

This invention relates to the integration of visual information, anatomic constraints, prior shape knowledge, and level set representations for the segmentation of medical images. An embodiment according to the present invention comprises a level set variational framework that uses a bi-directional boundary flow, an intensity-based regional component that maximizes the a posteriori segmentation probability, a physiology-based module that constrains the solution space and a term that accounts for shape-driven consistency. All modules are expressed in an energetic form and the resulting objective function is optimized using a gradient descent method.

Growing community of inventors

Trenton, NJ, United States of America

Mikael Rousson