Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Deep Learning for Automatic Segmentation of LGE CMR Images
The aim of the project is to develop a machine learning model for ventricular scar segmentation on Late Gadolinium Enhanced Cardiac Magnetic Resonance (LGE CMR) images.
Keywords: Machine Learning, ML, Deep Learning, Neural Networks, Data Analysis, Image Processing, Image Segmentation, CNN, Graph Neural Networks, Medical Imaging
Ventricular scar typically forms when a section of the myocardial wall is deprived of blood, most commonly caused by myocardial infarction. LGE CMR is the gold standard for scar imaging. It results in images with a contrast between normal myocardium (dark/no signal) and the scar tissue (bright). Because manual processing is time consuming and prone to errors, we want to make use of deep learning techniques. A large clinical dataset is available for this purpose.
Prerequisites: Programming experience in Python, experience with deep learning frameworks (PyTorch or Tensorflow), and familiarity with machine learning concepts (specifically for image classification or segmentation) are required.
Ventricular scar typically forms when a section of the myocardial wall is deprived of blood, most commonly caused by myocardial infarction. LGE CMR is the gold standard for scar imaging. It results in images with a contrast between normal myocardium (dark/no signal) and the scar tissue (bright). Because manual processing is time consuming and prone to errors, we want to make use of deep learning techniques. A large clinical dataset is available for this purpose.
Prerequisites: Programming experience in Python, experience with deep learning frameworks (PyTorch or Tensorflow), and familiarity with machine learning concepts (specifically for image classification or segmentation) are required.
The aim of this work is to develop a deep learning model that incorporates both intra-slice and inter-slice information for an accurate 3D ventricular scar segmentation. This can be done by implementing a 3D convolutional neural network, a recursive neural network, or a graph neural network.
The aim of this work is to develop a deep learning model that incorporates both intra-slice and inter-slice information for an accurate 3D ventricular scar segmentation. This can be done by implementing a 3D convolutional neural network, a recursive neural network, or a graph neural network.