Assessment of pulmonary function in coronavirus patients
AssigneeUniversity of Louisville Research Foundation, Inc.
InventorsAyman S. El-Baz, Ahmed Shalaby, Mohamed Elsharkawy, Ahmed Sharafeldeen, Ahmed Soliman, Ali Mahmoud, Harpal Sandhu, Guruprasad A. Giridharan
Life of this patent
Estimating the term…
Abstract
Assessment of pulmonary function in coronavirus patients includes use of a computer aided diagnostic (CAD) system to assess pulmonary function and risk of mortality in patients with coronavirus disease 2019 (COVID-19). The CAD system processes chest X-ray data from a patient, extracts imaging markers, and grades disease severity based at least in part on the extracted imaging markers, thereby distinguishing between higher risk and lower risk patients.
Claims14
A method for assessing pulmonary function, comprising:
- receiving medical image data that includes image data of at least one lung;
- segmenting image data of the at least one lung from other image data;
- modeling the segmented image data using a model with a central-symmetric system of pixel-pixel interactions;
- and
- classifying, using a neural network, pulmonary function as a first state or a second state based at least in part on the model;
- wherein modeling the segmented image data includes designating neighborhood sets for a plurality of different radii and determining Gibbs energy for each of the plurality of different radii;
- and
- wherein the classifying uses a plurality of neural networks, each receiving Gibbs energy from different radii as input, and a fusion neural network which uses the output of the plurality of neural networks as input.
A computer aided diagnostic system, comprising:
- at least one data processor;
- at least one memory;
- and
- program code stored on the at least one memory, the program code configured to be executed by the at least one processor to cause the at least one processor to:
- receive medical image data that includes image data of at least one lung;
- segment image data of the at least one lung from other image data;
- model the segmented image data using a model with a central-symmetric system of pixel-pixel interactions, including designation of neighborhood sets for a plurality of different radii;
- determine Gibbs energy for each of the plurality of different radii;
- and
- classify, using a plurality of neural networks, each configured to receive Gibbs energy from different radii as input, and a fusion neural network which uses the output of the plurality of neural networks as input, pulmonary function as a first state or a second state based at least in part on the model.
Dependencies are inferred from the claim text.