Siemens Aktiengesellschaft

Siemens Healthcare Gmbh

Siemens Healthineers Ag

Siemens Medical Solutions Usa, Inc.

Siemens Corporation

The University of British Columbia

Friedrich-alexander-universitat Erlangen-nürnberg

Rui Liao

Shun P Miao

Tommaso Mansi

Chenyang Xu

Ali Kamen

Matthias John

Dorin Comaniciu

Jan Boese

Yefeng Zheng

Sasa Grbic

Yiyong Sun

Bogdan Georgescu

Frank Sauer

Vivek Kumar Singh

Li Zhang

Norbert Strobel

Daguang Xu

Julian Krebs

Florin Cristian Ghesu

Terrence Chen

Shaohua Kevin Zhou

Ankur Kapoor

Christophe Chefd'hotel

Joachim Hornegger

Andreas Wimmer

Thomas Pheiffer

Alexander Brost

Hari Sundar

Michelle Xiaohong Yan

Shanhui Sun

Boris Mailhe

Marcus Pfister

Michael Suehling

Günter Lauritsch

Viorel Mihalef

Ali Khamene

Zhoubing Xu

Ingmar Voigt

Wen Wu

Noha Youssry El-Zehiry

Helene C Houle

Christoph Guetter

Jin-hyeong Park

Peter Mountney

Yanghai Tsin

Bimba Rao

Klaus J Kirchberg

Michael Sühling

Yue Zhang

Abdoul Aziz Amadou

Alois Nöttling

Pierre De Tournemire

Young-Ho Kim

Jiannan Zheng

Venkatesh Narasimha Murthy

Wei You

Yinxiao Liu

Ryan Leonard Spilker

Ahmet Tuysuzoglu

Sebastien Piat

Bibo Shi

Liron Yatziv

Xianjun Sam Zheng

Daniel Toth

Tanja Kurzendorfer

Anamaria Vizitiu

Erin Girard

Tobias Heimann

Florin-Cristian Ghesu

Yu Pang

Zhen Wang

Pavlo Dyban

Martin Willibald Koch

Bo Liu

Jarrod Collins

Walid Bekhtaoui

Caius Constantin Suliman

Klaus Kirchberg

Xianjun S Zheng

Sébastien Piat

Luc Duong

Uwe Kirschstein

Yunhao Tan

Martin Groher

Darko Zikic

Joseph Lucas

Marily Sarmiento

Matthias Schneider

Xudong Lv

Chen Qin

Zengming Shen

Systems and methods for automatically navigating a catheter in a patient are provided. An image of a current view of a catheter in a patient is received. A set of actions of a robotic navigation system for navigating the catheter from the current view towards a target view is determined using a machine learning based network. The catheter is automatically navigated in the patient from the current view towards the target view using the robotic navigation system based on the set of actions.

Smart image navigation for intracardiac echocardiography

The present application relates to a computer-implemented dynamic vessel roadmapping method. The method comprises generating a vessel roadmap library, the vessel roadmap library including a plurality of vessel roadmaps, wherein each vessel roadmap comprises vessel roadmap image and first and second alignment data, obtaining a real-time fluoroscopy image and corresponding real-time first and second fluoroscopy information, overlaying a vessel roadmap image of the vessel roadmap library with the real-time fluoroscopy image based on the first alignment data, the second alignment data, and the real time first and second fluoroscopy information and aligning the vessel roadmap image and the real-time fluoroscopy image based on the second alignment data and the real time second fluoroscopy information, wherein the second alignment data is derived from the corresponding vessel roadmap image.

Dynamic vessel roadmapping

A tip of a vascular catheter is detected in a sequence of vessel image frames obtained using x-rays. Within the vessel image frames, a proximal point corresponding to a vessel ostium is determined. The sequence of vessel image frames are cropped to an image area surrounding the proximal point to generate a cropped sequence of cropped vessel image frames. Within cropped vessel image frames not indicative of a contrast medium, the tip of the vascular catheter is detected, and the detected tip of the vascular catheter is tracked.

Method and system for vascular catheter tip detection in medical images

Systems and methods for tracking a location of an object of interest through a sequence of medical images are provided. First and second input medical images of a patient are received. The first input medical image comprises an annotation of a location of an object of interest. Features are extracted from the first and the second input medical images. A location of the object of interest in the second input medical image is determined using a machine learning based location predictor network based on the annotation of the location of the object of interest in the first input medical image and the extracted features from the first and the second input medical images. The location of the object of interest in the second input medical image is output. The machine learning based location predictor network is trained based on a comparison between 1) locations of a particular object in a sequence of training images determined during a forward tracking of the particular object through the sequence of training images and 2) locations of the particular object determined during a backward tracking of the particular object through the sequence of training images.

Semi-supervised tracking in medical images with cycle tracking

Systems and methods for training a machine learning based segmentation network are provided. A set of medical images, each depicting an anatomical object, in a first modality is received. For each respective medical image of the set of medical images, a synthetic image, depicting the anatomical object, in a second modality is generated based on the respective medical image. One or more augmented images are generated based on the synthetic image. One or more segmentations of the anatomical object are performed from the one or more augmented images using a machine learning based reference network. An uncertainty associated with segmenting the anatomical object from the respective medical image is computed based on results of the one or more segmentations. It is determined whether the respective medical image is suitable for training a machine learning based segmentation network based on the uncertainty. The machine learning based segmentation network is trained based on 1) the suitable medical images of the set of medical images and 2) annotations of the anatomical object determined using a machine learning based teacher network.

Cross domain segmentation with uncertainty-guided curriculum learning

Methods and systems for image registration using an intelligent artificial agent are disclosed. In an intelligent artificial agent based registration method, a current state observation of an artificial agent is determined based on the medical images to be registered and current transformation parameters. Action-values are calculated for a plurality of actions available to the artificial agent based on the current state observation using a machine learning based model, such as a trained deep neural network (DNN). The actions correspond to predetermined adjustments of the transformation parameters. An action having a highest action-value is selected from the plurality of actions and the transformation parameters are adjusted by the predetermined adjustment corresponding to the selected action. The determining, calculating, and selecting steps are repeated for a plurality of iterations, and the medical images are registered using final transformation parameters resulting from the plurality of iterations.

Method and system for image registration using an intelligent artificial agent

Systems and method for assisted catheter steering are provided. Instructions for steering a catheter within a patient are received. A graph defining paths between a plurality of configurations of a robotic catheter navigation system is constructed based on the received instructions. Each of the plurality of configurations are associated with a respective view of the patient. A path is determined in the graph to a target configuration of the plurality of configurations of the robotic catheter navigation system. The catheter is automatically steered within the patient based on the determined path in the graph to recover the respective view of the patient associated with the target configuration.

Assisted steering of intracardiac echocardiogram catheters

A method, apparatus, and computer readable storage medium are provided herein for constructing a representation of an annular structure associated with an anatomical object. The method includes receiving three-dimensional image data of the anatomical object and detecting at least a first landmark point and a second landmark point on the annular structure. A plane positioned between the first landmark point and the second landmark point, and oriented in accordance with a predefined angular relationship to a line connecting the first landmark point and the second landmark point is determined. A third landmark point on the annular structure which lies in the plane is also detected and the representation of the annular structure is generated using at least the first landmark point, the second landmark point, and the third landmark point. The representation is then outputted.

Annular structure representation

A method and system for 3D/3D medical image registration. A digitally reconstructed radiograph (DRR) is rendered from a 3D medical volume based on current transformation parameters. A trained multi-agent deep neural network (DNN) is applied to a plurality of regions of interest (ROIs) in the DRR and a 2D medical image. The trained multi-agent DNN applies a respective agent to each ROI to calculate a respective set of action-values from each ROI. A maximum action-value and a proposed action associated with the maximum action value are determined for each agent. A subset of agents is selected based on the maximum action-values determined for the agents. The proposed actions determined for the selected subset of agents are aggregated to determine an optimal adjustment to the transformation parameters and the transformation parameters are adjusted by the determined optimal adjustment. The 3D medical volume is registered to the 2D medical image using final transformation parameters resulting from a plurality of iterations.

Dilated fully convolutional network for 2D/3D medical image registration

In order to reduce computation time and provide more accurate solutions for bi-directional, multi-modal image registration, a learning-based unsupervised multi-modal deformable image registration method that does not require any aligned image pairs or anatomical landmarks is provided. A bi-directional registration function is learned based on disentangled shape representation by optimizing a similarity criterion defined on both latent space and image space.

Unsupervised deformable registration for multi-modal images

Systems and method are described for medical image segmentation. A medical image of a patient in a first domain is received. The medical image comprises one or more anatomical structures. A synthesized image in a second domain is generated from the medical image of the patient in the first domain using a generator of a task driven generative adversarial network. The one or more anatomical structures are segmented from the synthesized image in the second domain using a dense image-to-image network of the task driven generative adversarial network. Results of the segmenting of the one or more anatomical structures from the synthesized image in the second domain represent a segmentation of the one or more anatomical structures in the medical image of the patient in the first domain.

Cross domain medical image segmentation

Systems and methods are provided for determining a set of imaging parameters for an imaging system. A selection of an image is received from a set of images. A modification of certain quality measures is received for the selected image. The modified selected image is mapped to a set of imaging parameters of an imaging system based on the certain quality measures using a trained Deep Reinforcement Learning (DRL) agent.

Smart imaging using artificial intelligence

The disclosure relates to a method of determining a transformation between coordinate frames of sets of image data. The method includes receiving a model of a structure extracted from first source image data, the first source image data being generated according to a first imaging modality and having a first data format, wherein the model has a second data format, different from the first data format. The method also includes determining, using an intelligent agent, a transformation between coordinate frames of the model and first target image data, the first target image data being generated according to a second imaging modality different to the first imaging modality.

Determining a transformation between coordinate frames of sets of image data

Growing community of inventors

Princeton Junction, NJ, United States of America

Rui Liao