Ge Precision Healthcare LLC

General Electric Company

Jhimli Mitra

Soumya Ghose

Jed Douglas Pack

Thomas Kwok-Fah Foo

Prem Venugopal

Peter Michael Edic

David Martin Mills

Cynthia Elizabeth Landberg Davis

Desmond Teck Beng Yeo

Lowell Scott Smith

Bo Wang

Warren Lee

Luca Marinelli

Bryan P Bednarz

Michael J MacDonald

Asha Singanamalli

Roberta Marie Strigel

James Hartman Holmes

A computer-implemented method includes obtaining, via a processor, clinical images including vessels and generating, via the processor, straightened-out images for each coronary tree path within respective clinical images, The method also includes extracting, via the processor, segmented 3D image patches, determining, via the processor, overlapping binary mask volumes for each segment, and predicting, via the processor, pressure drops across the segmented image patches using a trained deep neural network.

System and method for deep-learning based estimation of coronary artery pressure drop

A computer-implemented method includes obtaining, via a processor, segmented image patches of a vessel along a coronary tree path and associated coronary flow distribution for respective vessel segments in the segmented image patches. The method also includes determining, via the processor, a pressure drop distribution along an axial length of the vessel from the segmented image patches and the associated coronary flow distribution. The method further includes determining, via the processor, critical points in the pressure drop distribution. The method even further includes detecting, via the processor, a presence of a stenosis based on the critical points in the pressure drop distribution.

System and method for detecting stenosis

A computer-implemented method includes generating, via a processor, synthetic vessels. The method also includes performing, via the processor, three-dimensional (3D) computational fluid dynamics (CFD) on the synthetic vessels for different flow rates to generate 3D CFD data. The method further includes extracting, via the processor, 3D image patches from the synthetic vessels. The method even further includes obtaining, via the processor, pressure drops across the 3D image patches from the 3D CFD data. The method yet further includes training, via the processor, a deep neural network utilizing the 3D image patches, the pressure drops, and associated flow rates to generate a trained deep neural network.

Systems and techniques that facilitate hybrid unsupervised and supervised image segmentation are provided. In various embodiments, a system can access a computed tomography (CT) image depicting an anatomical structure. In various aspects, the system can generate, via an unsupervised modeling technique, at least one class probability mask of the anatomical structure based on the CT image. In various instances, the system can generate, via a deep-learning model, an image segmentation based on the CT image and based on the at least one class probability mask.

Hybrid unsupervised and supervised image segmentation model

In accordance with the present disclosure, deep-learning techniques are employed to find anomalies corresponding to bleed events. By way of example, a deep convolutional neural network or combination of such networks may be trained to determine the location of a bleed event, such as an internal bleed event, based on ultrasound data acquired at one or more locations on a patient anatomy. Such a technique may be useful in non-clinical settings.

Automated detection and localization of bleeding

The subject matter discussed herein relates to multi-modal image alignment to facilitate biopsy procedures and post-biopsy procedures. In one such example, prostate structures (or other suitable anatomic features or structures) are automatically segmented in pre-biopsy MR and pre-biopsy ultrasound images. Thereafter, pre-biopsy MR and pre-biopsy ultrasound contours are aligned. To account for non-linear deformation of the imaged anatomic structure, a patient-specific transformation model is trained via deep learning based at least in part on the pre-biopsy ultrasound images. The pre-biopsy ultrasound images that are overlaid with the pre-biopsy MR contours and based off the deformable transformation model are then aligned with the biopsy ultrasound images. Such real-time alignment using multi-modality imaging techniques provides guidance during the biopsy and post-biopsy system.

Biopsy workflow using multimodal imaging

The subject matter discussed herein relates to the automatic, real-time registration of pre-operative magnetic resonance imaging (MRI) data to intra-operative ultrasound (US) data (e.g., reconstructed images or unreconstructed data), such as to facilitate surgical guidance or other interventional procedures. In one such example, brain structures (or other suitable anatomic features or structures) are automatically segmented in pre-operative and intra-operative ultrasound data. Thereafter, anatomic structure (e.g., brain structure) guided registration is applied between pre-operative and intra-operative ultrasound data to account for non-linear deformation of the imaged anatomic structure. MR images that are pre-registered to pre-operative ultrasound images are then given the same nonlinear spatial transformation to align the MR images with intra-operative ultrasound images to provide surgical guidance.

Deformable registration for multimodal images

A system and method for providing virtual real-time MRI-guidance for a biopsy outside of a conventional MRI scanner is described. MR images and ultrasound images of a region of a patient's body are simultaneously acquired during a pre-biopsy procedure. Respiratory states that the patient may experience during the biopsy are then determined from the acquired ultrasound images, and each respiratory state is associated with corresponding MR images. The MR images are indexed with their corresponding respiratory state. Ultrasound images are then acquired of the patient during a biopsy procedure. The respiratory state of the patient is determined from the ultrasound images, and the corresponding indexed MR images are displayed.

Image-guided biopsy techniques

A method is provided. The method includes acquiring simultaneously multiple magnetic resonance (MR) images and multiple ultrasound images of an anatomical region of a subject over a scanned duration. The method also includes training an unsupervised deep learning-based deformable registration network. This training includes training a MR registration subnetwork based on the multiple MR images to generate MR deformation and transformation vectors, training an ultrasound registration subnetwork based on the multiple ultrasound images to generate ultrasound deformation and transformation vectors, and training a MR-to-ultrasound subnetwork based the multiple MR images and the multiple ultrasound images to generate MR-to-ultrasound deformation and transformation vectors between corresponding pairs of MR images and ultrasound images at each time point.

Growing community of inventors

Niskayuna, NY, United States of America

Jhimli Mitra