Atrial Scar
Atrial scar, the formation of non-functional cardiac tissue in the atria, is a significant factor in atrial fibrillation (AFib) and other heart conditions. Current research heavily focuses on accurately segmenting and quantifying atrial scar using advanced image analysis techniques, primarily employing deep learning models such as convolutional neural networks (CNNs) and variations like U-Net architectures, often incorporating multi-sequence magnetic resonance imaging (MRI) data for improved accuracy. Precise scar mapping is crucial for personalized treatment strategies in AFib, enabling better risk stratification and potentially improving the effectiveness of interventions like cardiac resynchronization therapy. This improved diagnostic capability holds significant promise for enhancing patient care and outcomes.
Papers
Joint Deep Learning for Improved Myocardial Scar Detection from Cardiac MRI
Jiarui Xing, Shuo Wang, Kenneth C. Bilchick, Amit R. Patel, Miaomiao Zhang
Multitask Learning for Improved Late Mechanical Activation Detection of Heart from Cine DENSE MRI
Jiarui Xing, Shuo Wang, Kenneth C. Bilchick, Frederick H. Epstein, Amit R. Patel, Miaomiao Zhang