Siemens Healthcare Gmbh

Siemens Healthineers Ag

Deutsches Krebsforschungszentrum

Max Schöbinger

Puneet Sharma

Dorin Comaniciu

Mehmet Akif Gulsun

Diana Ioana Stoian

Shaohua Kevin Zhou

Ali Kamen

Tommaso Mansi

Vivek Kumar Singh

Thomas Redel

Sasa Grbic

Tiziano Passerini

Lucian Mihai Itu

David D Liu

Saikiran Rapaka

Michael Scheuering

Zhoubing Xu

Ingmar Voigt

Michael Wels

Razvan Ionasec

Helene C Houle

Dominik Neumann

Chris Schwemmer

Mingqing Chen

Julian Krebs

Jan Kretschmer

Michael Sühling

Jing Lu

Felix Denzinger

Tae Soo Kim

Hans-Peter Meinzer

He Zhang

Sebastian Faby

Sebastian Seifert

Joel Mancina

Ivo Wolf

Systems and methods for automated assessment of a vessel are provided. One or more input medical images of a vessel of a patient are received. A plurality of vessel assessment tasks for assessing the vessel is performed using a machine learning based model trained using multi-task learning. The plurality of vessel assessment tasks comprises segmentation of reference walls of the vessel from the one or more input medical images and segmentation of lumen of the vessel from the one or more input medical images. Results of the plurality of vessel assessment tasks are output.

Coronary lumen and reference wall segmentation for automatic assessment of coronary artery disease

Systems and methods for automated assessment of a vessel are provided. One or more input medical images of a vessel of a patient are received. A plurality of vessel assessment tasks for assessing the vessel is performed using a machine learning based model trained using multi-task learning. The plurality of vessel assessment tasks are performed by the machine learning based model based on shared features extracted from the one or more input medical images. Results of the plurality of vessel assessment tasks or a combination of the results of the plurality of vessel assessment tasks are output.

Multi-task learning framework for fully automated assessment of coronary artery disease

A method and apparatus for deep learning based automatic bone removal in medical images, such as computed tomography angiography (CTA) volumes, is disclosed. Bone structures are segmented in a 3D medical image of a patient by classifying voxels of the 3D medical image as bone or non-bone voxels using a deep neural network trained for bone segmentation. A 3D visualization of non-bone structures in the 3D medical image is generated by removing voxels classified as bone voxels from a 3D visualization of the 3D medical image.

Deep learning based bone removal in computed tomography angiography

A method and system for determining hemodynamic indices, such as fractional flow reserve (FFR), for a location of interest in a coronary artery of a patient is disclosed. Medical image data of a patient is received. Patient-specific coronary arterial tree geometry of the patient is extracted from the medical image data. Geometric features are extracted from the patient-specific coronary arterial tree geometry of the patient. A hemodynamic index, such as FFR, is computed for a location of interest in the patient-specific coronary arterial tree based on the extracted geometric features using a trained machine-learning based surrogate model. The machine-learning based surrogate model is trained based on geometric features extracted from synthetically generated coronary arterial tree geometries.

Method and system for purely geometric machine learning based fractional flow reserve

A method for determining functional severity of a stenosis includes: (a) generating a simulated perfusion map from a calculated blood flow; (b) comparing the simulated perfusion map to a measured perfusion map to identify a degree of mismatch therebetween, the measured perfusion map representing perfusion in a patient; (c) modifying a parameter in a model used in calculating the blood flow when the degree of mismatch meets or exceeds a predefined threshold; (d) computing a hemodynamic quantity from the simulated perfusion map when the degree of mismatch is less than the predefined threshold, the hemodynamic quantity being indicative of the functional severity of the stenosis; and (e) displaying the hemodynamic quantity. Systems for determining functional severity of a stenosis are described.

Determining functional severity of stenosis

Growing community of inventors

Hirschaid, Germany

Max Schöbinger