Siemens Aktiengesellschaft

Siemens Healthcare Gmbh

Ludwig-maxmilians-universitat

Sascha Seifert

Dorin Comaniciu

Martin Huber

Alexander Cavallaro

Shaohua Kevin Zhou

David D Liu

Michael Suehling

Michael Kelm

Michael Wels

Martin Kramer

Maria Jimena Costa

Adrian Barbu

Dominik Bernhardt

Helmut König

Rüdiger Bertsch

Roland Brill

Johannes Feulner

Marisa Petri

A method and apparatus for detecting vascular landmarks in a 3D image volume, such as a CT volume, is disclosed. One or more guide slices are detected in a 3D image volume. A set of landmark candidates for multiple target vascular landmarks are then detected based on the guide slices. A node potential value for each landmark candidate is generated based on an error value determined using spatial histogram-based error regression, and edge potential values for pairs of landmark candidates are generated based on a bifurcation analysis of the image volume using vessel tracing. The optimal landmark candidate for each target landmark is then determined using a Markov random field model based on the node potential values and the edge potential values.

System and method for detecting landmarks in a three-dimensional image volume

A computer network system and a method are disclosed for accessing a dose image database for medical imaging using ionizing radiation via an imaging device. An embodiment includes a multiplicity of imaging devices connected via a network connection to the dose image database, each imaging device including a transmit unit to transmit the images captured by the imaging device to the dose image database. An allocation between an image or a class of images, a dose measurement value, an image quality measurement value and optionally further medical metadata are stored in the dose image database. A control unit is included to exchange date with the dose image database and to generate control variables automatically while accessing the dose image database depending on at least one selection parameter to be defined, the parameters being forwarded via a network connection to at least one imaging device to control the imaging.

Network system and method for controlling a computer tomograph

A method and apparatus for hierarchical parsing and semantic navigation of a full or partial body computed tomography CT scan is disclosed. In particular, organs are segmented and anatomic landmarks are detected in a full or partial body CT volume. One or more predetermined slices of the CT volume are detected. A plurality of anatomic landmarks and organ centers are then detected in the CT volume using a discriminative anatomical network, each detected in a portion of the CT volume constrained by at least one of the detected slices. A plurality of organs, such as heart, liver, kidneys, spleen, bladder, and prostate, are detected in a sense of a bounding box and segmented in the CT volume, detection of each organ bounding box constrained by the detected organ centers and anatomic landmarks. Organ segmentation is via a database-guided segmentation method.

Method and system for hierarchical parsing and semantic navigation of full body computed tomography data

A method is disclosed for assigning measurement data of a body of a patient to information data related to the same body. The method includes providing annotated measurement data, providing annotated information data, translating the first group of annotations into a first group of universal annotations and the second group of annotations into a second group of universal medical annotations in a universal annotation ontology management system, comparing the universal annotations of the first group of universal annotations with the universal annotations of the second group of universal annotations, and assigning the universal annotations to each other. An assignment system and a universal annotation ontology management system are also disclosed.

Assignment of measurement data to information data

Methods and device are disclosed for data retrieval. At first images and reports are analyzed by respective parser units to detect both structures and text passages that are related to respective structures and text passages of a knowledge data-base. The detected structures and text passages are stored together with a unique resource located that identifies the respective structure and/or text passage at the knowledge database in a semantic annotation database. In addition a feature extraction can be performed to provide specific features of the images and/or regions of the images, whereby the features are stored in an image feature database. Finally an input query can ask questions that are used to provide a result to the query based on the semantic annotation database and the image feature database. The methods and devices may be used for data preparation and data retrieval of medical images and associated medical reports.

Methods and devices for data retrieval

A method and system for the diagnosis of 3D images are disclosed, which significantly cuts the time required for the diagnosis. The 3D images are for example an image volume dataset of a magnetic resonance tomography system which is saved in an RIS or PACS system. In at least one embodiment, the diagnostic finding are partially automatically generated, and details of the position, size and change in pathological structures are compared to previous diagnostic findings are generated automatically. As a result of this automation the diagnostic work of radiologists is significantly reduced.

Computer-aided evaluation of an image dataset

Methods and a system are disclosed for providing a mechanism for searching and extracting three-dimensional regions of interest in image archives. In at least one embodiment, a textual search query serves as input and is processed in order to provide a newly generated query-specific volume image, including computed sub-volumes covering the anatomical structure the query refers to. The query is input via a graphical search interface and the sub-volumes are outputted also via the graphical search interface.

Query-specific generation and retrieval of medical volume images

A method and system for fully automatic segmentation the prostate in multi-spectral 3D magnetic resonance (MR) image data having one or more scalar intensity values per voxel is disclosed. After intensity standardization of multi-spectral 3D MR image data, a prostate boundary is detected in the multi-spectral 3D MR image data using marginal space learning (MSL). The detected prostate boundary is refined using one or more trained boundary detectors. The detected prostate boundary can be split into patches corresponding to anatomical regions of the prostate and the detected prostate boundary can be refined using trained boundary detectors corresponding to the patches.

Growing community of inventors

Königsbach-Stein, Germany

Sascha Seifert