We have developed software for whole heart and heart substructures segmentation from CT and MRI images. The software includes three new methods for extracting the whole heart and individual heart structures (left ventricle, right ventricle, left atrium, right atrium, pulmonary arteries, aorta) in both image modalities with high accuracy and its computation takes only a few seconds.
Bi-ventricles and myocardium segmentation and quantification
Automatic cardiac MRI segmentation, including left and right ventricular endocardium and epicardium, plays an essential role in clinical diagnosis by providing crucial information about cardiac function. Determining heart chamber properties, such as volume or ejection fraction, directly relies on their accurate segmentation. Therefore, we have developed software that includes a new deep learning method for the segmentation of ventricles and myocardium as well as the calculation of their volume.
One-click interactive left atrial appendage segmentation from cardiovascular CT images
We have developed a software package for a one-click segmentation of the LAA from cardiovascular CT images. The user has to select a single seed point inside the LAA, and the segmentation algorithm creates a 3D model of the appendage. Our software determines the threshold, detects the centreline connecting the seed point and the centre of the left atrium, performs the centreline based LAA segmentation, detects the location of the LAA orifice and creates a 3D model of the LAA.
