US 11,875,892 B2
Segmentation of medical images
Ayman S. El-Baz, Louisville, KY (US); Ahmed Soliman, Louisville, KY (US); Moumen El-Melegy, Assuit (EG); and Mohamed Abou El-Ghar, El Mansoura (EG)
Assigned to University of Louisville Research Foundation, Inc., Louisville, KY (US)
Appl. No. 16/628,795
Filed by UNIVERSITY OF LOUISVILLE RESEARCH FOUNDATION, INC., Louisville, KY (US); and SCIENCE AND TECHNOLOGY DEVELOPMENT FUND, Cairo (EG)
PCT Filed Jul. 7, 2018, PCT No. PCT/US2018/041168
§ 371(c)(1), (2) Date Jan. 6, 2020,
PCT Pub. No. WO2019/010470, PCT Pub. Date Jan. 10, 2019.
Claims priority of provisional application 62/529,788, filed on Jul. 7, 2017.
Prior Publication US 2020/0203001 A1, Jun. 25, 2020
Int. Cl. G16H 30/40 (2018.01); G06T 7/11 (2017.01); G06N 20/20 (2019.01); G06N 3/08 (2023.01); G06N 7/01 (2023.01)
CPC G16H 30/40 (2018.01) [G06N 3/08 (2013.01); G06N 7/01 (2023.01); G06N 20/20 (2019.01); G06T 7/11 (2017.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method for segmenting medical images comprising:
integrating image descriptors with a three-dimensional neural network, the image descriptors including a medical image, a Gibbs energy for a Markov-Gibbs random field model of the medical image, and an adaptive shape prior model of the medical image;
generating, using the three-dimensional neural network, probabilities for a goal region; and
designating, based on the generated probabilities, the goal region in the medical image.