Siemens Medical Solutions Usa, Inc.

Siemens Healthcare Gmbh

Johns Hopkins University

Siemens Corporation

Siemens Aktiengesellschaft

Sebastian Vogt

Frank Sauer

Ali Khamene

Dorin Comaniciu

Jeffrey H Siewerdsen

Gerhard Kleinszig

Christophe Chefd'hotel

Jens Gühring

Bogdan Georgescu

Ali Kamen

Sasa Grbic

Bernhard Geiger

Michael Scheuering

Chenyang Xu

Estelle Camus

Zhoubing Xu

Razvan Ioan Ionasec

Helene C Houle

Jens Guehring

Yiyong Sun

Siqi Liu

Fred S Azar

Wolfgang Wein

Xiaolei Sharon Huang

Florin-Cristian Ghesu

Ruhan Sa

Awais Mansoor

Adam S Wang

Razvan Chisu

Runze Han

Systems and methods for assessing a disease are provided. An input medical image in a first modality is received. Lungs are segmented from the input medical image using a trained lung segmentation network and abnormality patterns associated with the disease are segmented from the input medical image using a trained abnormality pattern segmentation network. The trained lung segmentation network and the trained abnormality pattern segmentation network are trained based on 1) synthesized images in the first modality generated from training images in a second modality and 2) target segmentation masks for the synthesized images generated from training segmentation masks for the training images. An assessment of the disease is determined based on the segmented lungs and the segmented abnormality patterns.

Assessment of abnormality patterns associated with COVID-19 from x-ray images

A method, computer system, and a computer-readable medium for registering one or more structures to a desired orientation for planning and guidance for surgery is provided. The method includes in a preoperative stage, obtaining one or more 3D models of one or more structures from one or more CT images using an image processing segmentation technique or a manual segmentation technique; in the preoperative stage, registering the one or more structures to a template that is adapted to an alternating registration for a patient-specific shape and pose for a desired reduction and corresponding reduction transformations; in an intraoperative stage, mapping the one or more structures to one or more radiographs via a 3D-2D registration that iteratively optimizes a similarity metric between acquired and simulated radiographs; and in the intraoperative stage, providing an output that is representative of a radiograph or a 3D tomographic representation to provide guidance to a user.

Method and system for registering multiple structures in medical images

The invention describes a device suspension arrangement comprising a ceiling region, at least one mobile device comprising a ceiling interface with at least one freely rotatable element arranged to partially protrude from the ceiling interface to facilitate movement of the suspended device to an arbitrary ceiling position; and at least one magnetic field generator realised to generate a magnetic field between the ceiling region and the ceiling interface of a mobile device. The invention further describes a mobile device for use in such a device suspension arrangement.

Device suspension arrangement

A method of generating a preview of at least one low-dose x-ray image includes the followings steps: obtaining an initial volumetric representation of a patient from an x-ray device; creating at least one x-ray image projection from the initial volumetric representation; injecting correlated noise into at least one of the x-ray image projections; and processing the noise-injected x-ray image projections to create at least one preview of a patient-specific low-dose x-ray for showing to a user. There are also described a device for generating at least one preview of a low-dose x-ray image, a corresponding imaging system, and a non-transitory computer readable medium.

Method and device for generating a low-dose X-ray image preview, imaging system and computer program product

A system and method for instrument placement using an image based navigation system is disclosed. A target of interest is identified in a medical image of a patient. An image plane is displayed that goes through a center of the target. The image plane has a configurable orientation. The image plane is used to select a path for an instrument from a position on the patient's skin to the center of the target. A trajectory plane is viewed from a tip of the instrument to the center of the target. The trajectory plane reflects an orientation of the instrument. A particular trajectory plane is selected that is representative of a desired orientation of the instrument. An image of the particular trajectory plane is frozen. The instrument can then be inserted using a virtual guide and is navigated toward the target.

Method for augmented reality instrument placement using an image based navigation system

A method and apparatus for presenting three-dimensional data to a physician is provided to facilitate the flexible navigation of an endoscope and surgical instruments with respect to anatomical structures. In accordance with a first embodiment a first set of data corresponding to a three dimensional model of a patient's anatomy is received. This three-dimensional model may be rendered from images taken in CT or MRI scanning, as discussed above. In accordance with this embodiment, this model is then combined with a second set of data corresponding to a view obtained from an endoscope. In another embodiment, the view from the illustrative endoscope is displayed as an inset image on the display of the three-dimensional image. In yet another embodiment, the three-dimensional image comprises a graphical representation of at least a first surgical instrument, such as said endoscope. The surgeon may select among various combinations of views and may zoom in or out from any particular view.

Method and apparatus for minimally invasive surgery using endoscopes

A method and system for modeling the aortic valve in 4D image data, such as 4D CT and echocardiography, is disclosed. An initial estimate of a physiological aortic valve model is determined for at least one reference frame of a 4D image sequence based on anatomic features in the reference frame. The initial estimate is refined to generate a final estimate in the reference frame. A dynamic model of the aortic valve is then generated by estimating the physiological aortic valve model for each remaining frame of the 4D image sequence based on the final estimate in the reference frame. The aortic valve can be quantitatively evaluated using the dynamic model.

Method and system for automatic quantification of aortic valve function from 4D computed tomography data using a physiological model

A method for visualization of dynamic three-dimensional (3D) virtual objects comprises storing a plurality of static 3D key-models respectively describing a dynamic 3D object in at least one of a number of poses and shapes; and rendering the dynamic 3D object by interpolation of the 3D key-models by performing the interpolation in a vertex shader program of a programmable graphics processing unit (GPU).

Method and system for visualization of dynamic three-dimensional virtual objects

A method for augmented reality navigation of a medical intervention includes providing a stereoscopic head mounted display, the display including a pair of stereo viewing cameras, at least one tracking camera, and a stereoscopic guidance display. During a medical intervention on a patient, the patient's body pose is determined from a rigid body transformation between the tracking camera and frame markers on the scanning table, and the pose of an intervention instrument with respect to the table is determined. A visual representation of the patient overlaid with an image of the intervention target, the instrument, and a path for guiding the instrument to perform said medical intervention is displayed in the stereoscopic guidance display.

System and method for augmented reality navigation in a medical intervention procedure

Exemplary systems and methods for performing registration applications are provided. An exemplary system includes a central processing unit (CPU) for transferring a plurality of images to a graphics processing unit (GPU); wherein the GPU performs a registration application on the plurality of images to produce a registration result, and wherein the GPU returns the registration result to the CPU. An exemplary method includes the steps of transferring a plurality of images from a central processing unit (CPU) to a graphics processing unit (GPU); performing a registration application on the plurality of images using the GPU; transferring the result of the step of performing from the GPU to CPU.

GPU-based image manipulation method for registration applications

A system and corresponding method for flexible generation of digitally reconstructed radiograph (DRR) images on a graphics processing unit (GPU) are provided, the system including a processor, an imaging adapter in signal communication with the processor for receiving volumetric data, an integration unit in signal communication with the processor for integrating the volumetric data into incremental line integrals, and a modeling unit in signal communication with the processor for modeling composite line integrals from the incremental line integrals; and the corresponding method including receiving three-dimensional (3D) volumetric data into a graphics pipeline, integrating the 3D volumetric data into incremental line integrals along a plurality of viewing rays, modeling composite line integrals from the incremental line integrals, and adding the incremental line integrals for each composite line integral to form pixels of the DRR image.

Flexible generation of digitally reconstructed radiographs

A method of aligning a pair of images with a first image and a second image, wherein said images comprise a plurality of intensities corresponding to a domain of points in a D-dimensional space includes identifying feature points on both images using the same criteria, computing a feature vector for each feature point, measuring a feature dissimilarity for each pair of feature vectors, wherein a first feature vector of each pair is associated with a first feature point on the first image, and a second feature vector of each pair is associated with a second feature point on the second image. A correspondence mapping for each pair of feature points is determined using the feature dissimilarity associated with each feature point pair, and an image transformation is defined to align the second image with the first image using one or more pairs of feature points that are least dissimilar.

Growing community of inventors

Princeton, NJ, United States of America

Sebastian Vogt