公开(公告)号：US12109061B2

公开(公告)日：2024-10-08

申请号：US17195694

申请日：2021-03-09

Applicant: SIEMENS HEALTHINEERS AG

Inventor： Lucian Mihai Itu ,  Tiziano Passerini ,  Saikiran Rapaka ,  Puneet Sharma ,  Chris Schwemmer ,  Max Schoebinger ,  Thomas Redel ,  Dorin Comaniciu

IPC: G06T7/11 ,  A61B5/00 ,  A61B5/026 ,  A61B6/00 ,  A61B6/03 ,  A61B6/50 ,  A61B8/06 ,  A61B8/08 ,  G06F18/21 ,  G06F18/22 ,  G06F18/2413 ,  G06T7/00 ,  G06V10/42 ,  G06V10/776 ,  G16H20/00 ,  G16H30/40 ,  G16H50/20 ,  G16H50/50 ,  A61B5/02 ,  A61B6/46 ,  A61B8/00 ,  G16H30/20

CPC classification number: A61B6/5217 ,  A61B5/026 ,  A61B5/7267 ,  A61B6/032 ,  A61B6/504 ,  A61B6/507 ,  A61B8/06 ,  A61B8/065 ,  A61B8/5223 ,  G06F18/217 ,  G06F18/22 ,  G06F18/2413 ,  G06T7/0012 ,  G06T7/11 ,  G06V10/42 ,  G06V10/776 ,  G16H20/00 ,  G16H30/40 ,  G16H50/20 ,  G16H50/50 ,  A61B5/02007 ,  A61B5/02028 ,  A61B5/0263 ,  A61B5/743 ,  A61B6/469 ,  A61B8/469 ,  A61B2576/00 ,  G06T2200/04 ,  G06T2207/10072 ,  G06T2207/10076 ,  G06T2207/20081 ,  G06T2207/30101 ,  G06T2207/30104 ,  G16H30/20

Abstract: In hemodynamic determination in medical imaging, the classifier is trained from synthetic data rather than relying on training data from other patients. A computer model (in silico) may be perturbed in many different ways to generate many different examples. The flow is calculated for each resulting example. A bench model (in vitro) may similarly be altered in many different ways. The flow is measured for each resulting example. The machine-learnt classifier uses features from medical scan data for a particular patient to estimate the blood flow based on mapping of features to flow learned from the synthetic data. Perturbations or alterations may account for therapy so that the machine-trained classifier may estimate the results of therapeutically altering a patient-specific input feature. Uncertainty may be handled by training the classifier to predict a distribution of possibilities given uncertain input distribution. Combinations of one or more of uncertainty, use of synthetic training data, and therapy prediction may be provided.

公开(公告)号：US20240423575A1

公开(公告)日：2024-12-26

申请号：US18825275

申请日：2024-09-05

Applicant: Siemens Healthineers AG

Inventor： Lucian Mihai Itu ,  Tiziano Passerini ,  Saikiran Rapaka ,  Puneet Sharma ,  Chris Schwemmer ,  Max Schoebinger ,  Thomas Redel ,  Dorin Comaniciu

IPC: A61B6/00 ,  A61B5/00 ,  A61B5/02 ,  A61B5/026 ,  A61B6/03 ,  A61B6/46 ,  A61B6/50 ,  A61B8/00 ,  A61B8/06 ,  A61B8/08 ,  G06F18/21 ,  G06F18/22 ,  G06F18/2413 ,  G06T7/00 ,  G06T7/11 ,  G06V10/42 ,  G06V10/776 ,  G16H20/00 ,  G16H30/20 ,  G16H30/40 ,  G16H50/20 ,  G16H50/50

Abstract: In hemodynamic determination in medical imaging, the classifier is trained from synthetic data rather than relying on training data from other patients. A computer model (in silico) may be perturbed in many different ways to generate many different examples. The flow is calculated for each resulting example. A bench model (in vitro) may similarly be altered in many different ways. The flow is measured for each resulting example. The machine-learnt classifier uses features from medical scan data for a particular patient to estimate the blood flow based on mapping of features to flow learned from the synthetic data. Perturbations or alterations may account for therapy so that the machine-trained classifier may estimate the results of therapeutically altering a patient-specific input feature. Uncertainty may be handled by training the classifier to predict a distribution of possibilities given uncertain input distribution. Combinations of one or more of uncertainty, use of synthetic training data, and therapy prediction may be provided.