Academic Lead: Alistair Young
Clinical Area: Cardiology
Partner: Siemens Healthineers
Atrial fibrillation (AF) is the most common cardiac arrhythmia, affecting more than 33m people worldwide, and increasing the risk of stroke heart failure and death. The most common treatment for atrial fibrillation is catheter ablation - it involves inserting a flexible catheter into the blood vessels, and using local heating or freezing to destroy the abnormal tissue causing the atrial fibrillation. Whilst catheter ablation is common, it has a high re-occurrence rate (20-50%).
Identifying the geometry and volume of the left atrial (heart chamber) is incredibly useful in confirming diagnosis and prognosis of various heart diseases, including atrial fibrillation. Currently, the left atrial volume is estimated using 2 different measurements - width and length. This method is somewhat limited and can result in inaccurate calculations, and therefore clinical decisions.
We are developing an AI tool, in collaboration with Siemens Healthineers, for the automatic analysis of the atria and ventricles (including automatic segmentation and fibrosis detection) from MRI images. The tool would be implemented in-line so that the resulting indices, mesh and fibrosis information are available as reports at the time of scanning.
The AI tool will infer the 3D shape, volume and surface area of the left atrial, to a greater degree of accuracy than the current bi-plane method. In the future, the results will be extended to include risk prediction scores and highlight sites appropriate for ablation treatment.
Published Academic Papers
- Hao Xu, Steven Williams, Michelle Williams, David E. Newby, Jonathan Taylor, Radhouene Neji, Karl Kunze, Steven Niederer, Alistair Young. (2023).
Deep Learning Estimation of Three-Dimensional Left Atrial Shape from Two-Chamber and Four-Chamber Cardiac Long Axis Views. European Heart Journal