SFMC23

Fluid Dynamic Tool for Cardiac Diseases Analysis

  • Groun, Nourelhouda (universidad politecnica de madrid)
  • Villalba-Orero, Maria (Centro Nacional de Investigaciones Cardiovasc)
  • Lara-Pezzi, Enrique (Centro Nacional de Investigaciones Cardiovasc)
  • Valero, Eusebio (universidad politecnica de madrid)
  • Garicano-Mena, Jesus (universidad politecnica de madrid)
  • Le Clainche, Soledad (universidad politecnica de madrid)

Please login to view abstract download link

In this work we are investigating a fluid dynamics tool, named the higher order dynamic mode decomposition (HODMD) , for the first time in the medical field. HODMD is a fully data-driven method widely used in fluid dynamics applications. In this work HODMD is applied for the first time, to the best of our knowledge, for the analysis of cardiac images. This algorithm, which is employed as feature extraction technique, is used to analyze different echocardiography datasets, taken from mice in healthy conditions and mice diagnosed with different cardiac diseases (Diabetic Cardiomyopathy, Obesity, TAC Hypertrophy and Myocardial Infarction). The main purpose of this approach is to identify and extract dominant features related to the various cardiac diseases. which will be used to classify the different cardiac diseases using convolutional neural networks (CNNs).