Left ventricular filtering and segmentation and detection of a cardiac cycle in echocardiogram videos

• Grant number: 20/08630-7
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: September 01, 2020
• End date: August 31, 2021
• Field of knowledge: Engineering - Biomedical Engineering
• Principal Investigator: Regina Célia Coelho
• Grantee: Isabela Garcia Mello e Silva
• Host Institution: Instituto de Ciência e Tecnologia (ICT). Universidade Federal de São Paulo (UNIFESP). Campus São José dos Campos. São José dos Campos , SP, Brazil

Abstract

Cardiovascular diseases (CVDs) are the most significant cause of death in the world. The first step in controlling and treating these diseases is an accurate and early diagnosis, which can be achieved with the aid of imaging systems, such as echocardiography. Transthoracic echocardiography is widely used to assess the heart's ventricular chambers, notably the left ventricle (LV), which plays a very important role in the heart's pumping function. Evaluate the dynamics of the LV can help in obtaining information relevant to the diagnosis of CVDs. One way to improve the diagnostic process is to make the delineation (or segmentation) of the left ventricular wall, considering its movements during the cardiac cycle in echocardiographic images. In order to obtain a good result in the segmentation, an important step is the filtering for the removal of speckles noise before the segmentation, since such noises can influence the quality and precision of the results. Therefore, the goal of this project is to develop a robust computational tool for filtering, segmenting the LV and detect a cardiac cicle in echocardiogram videos. Specifically, the purpose of the proposed tool is to filter the images and segment the LV walls (internal and external) in the long axis parasternal section, in the video frames of a cardiac cycle, to assist the analysis of cardiac function in clinical practice.