US 10,888,234 B2
Method and system for machine learning based assessment of fractional flow reserve
Puneet Sharma, Princeton Junction, NJ (US); Ali Kamen, Skillman, NJ (US); Bogdan Georgescu, Plainsboro, NJ (US); Frank Sauer, Princeton, NJ (US); Dorin Comaniciu, Princeton Junction, NJ (US); Yefeng Zheng, Princeton Junction, NJ (US); Hien Nguyen, Houston, TX (US); and Vivek Kumar Singh, Princeton, NJ (US)
Assigned to Siemens Healthcare GmbH, Erlangen (DE)
Filed by Siemens Healthcare GmbH, Erlangen (DE)
Filed on Mar. 4, 2019, as Appl. No. 16/291,825.
Application 16/291,825 is a continuation of application No. 15/958,483, filed on Apr. 20, 2018, granted, now 10,258,244.
Application 15/958,483 is a continuation of application No. 15/616,380, filed on Jun. 7, 2017, granted, now 9,974,454, issued on May 22, 2018.
Application 15/616,380 is a continuation of application No. 14/516,163, filed on Oct. 16, 2014, granted, now 9,700,219, issued on Jul. 11, 2017.
Claims priority of provisional application 61/891,920, filed on Oct. 17, 2013.
Prior Publication US 2019/0200880 A1, Jul. 4, 2019
Int. Cl. G06T 7/00 (2017.01); A61B 5/026 (2006.01); A61B 6/00 (2006.01); G06T 7/20 (2017.01); G06K 9/62 (2006.01); G16H 50/30 (2018.01); G16H 50/50 (2018.01); A61B 5/00 (2006.01); A61B 6/03 (2006.01); A61B 8/06 (2006.01); G06K 9/46 (2006.01); G16H 50/20 (2018.01); A61B 8/08 (2006.01); A61B 8/12 (2006.01); A61B 8/00 (2006.01)
CPC A61B 5/026 (2013.01) [A61B 5/0261 (2013.01); A61B 5/0263 (2013.01); A61B 5/7264 (2013.01); A61B 5/7267 (2013.01); A61B 5/7282 (2013.01); A61B 6/032 (2013.01); A61B 6/504 (2013.01); A61B 6/507 (2013.01); A61B 6/5217 (2013.01); A61B 8/06 (2013.01); G06K 9/46 (2013.01); G06K 9/6256 (2013.01); G06T 7/0012 (2013.01); G06T 7/0016 (2013.01); G06T 7/20 (2013.01); G16H 50/20 (2018.01); G16H 50/30 (2018.01); G16H 50/50 (2018.01); A61B 6/563 (2013.01); A61B 8/0891 (2013.01); A61B 8/12 (2013.01); A61B 8/5223 (2013.01); A61B 8/565 (2013.01); G06T 2207/10081 (2013.01); G06T 2207/10088 (2013.01); G06T 2207/10101 (2013.01); G06T 2207/10132 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30048 (2013.01); G06T 2207/30104 (2013.01); G06T 2211/404 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for analyzing an effect of a treatment scenario, comprising:
extracting features for a stenosis of interest from medical image data of a patient;
determining a first fractional flow reserve (FFR) value for the stenosis of interest based on the extracted features using a trained machine-learning based mapping, wherein the trained machine-learning based mapping is trained based on geometric features extracted from synthetically generated stenosis geometries that are not based on patient-specific data;
determining a second FFR value for the stenosis of interest based on one or more modified values of the extracted features using the trained machine-learning based mapping, the one or more modified values of the extracted features reflecting the treatment scenario; and
analyzing the effect of the treatment scenario based on the first FFR and the second FFR.