<ul><li>Researchers have developed a deep learning framework for unsupervised clustering of myocardial fibers in cardiac diffusion tensor imaging (DTI) data.</li><li>The framework combines a Bidirectional Long Short-Term Memory (LSTM) network to capture local sequential information along fibers, with a Transformer autoencoder to learn global shape features and incorporate anatomical context.</li><li>By clustering the learned representations using a density-based algorithm, the framework successfully identifies 33 to 62 robust clusters, capturing subtle differences in fiber trajectories.</li><li>This approach has the potential to improve surgical planning, characterize disease-related remodeling, and advance personalized cardiac care.</li></ul>

Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging

Discover more