Keywords: Myocardium, Segmentation, Late Gadolinium Enhancement; Myocardial Infarction; Machine Learning
Motivation: Late Gadolinium Enhancement (LGE) is the reference standard for assessing myocardial viability. LGE also shows the presence and extent of microvascular obstruction (MVO) or no-reflow, a marker of severe myocardial injury. Automatic segmentation and classification techniques have been developed to identify LGE-enhanced regions, but do not address areas of no-reflow.
Goal(s): Develop a robust and reproducible solution to automatically assess MI and MVO presence and extent.
Approach: The proposed RAMI.dl combines deep learning-based segmentation and radiomics LGE feature extraction to improve MI and MVO diagnosis.
Results: RAMI.dl distinguishes normal, MI and MVO with high accuracy and automatically computes scar tissue and no-reflow volumes.
Impact: RAMI.dl combines deep learning and radiomics to automatically detect and quantify the regions of microvascular obstruction and scar tissue from LGE images, essential in the diagnosis and prognosis of patients suffering from myocardial infarction.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords