Meeting Banner
Abstract #0634

Automated Left Ventricular Volumetric Quantitation from Short-axis CMR Images with Machine Learning using a Deep Convolutional Neural Network

James W Goldfarb1, Jie J Cao1, and Julian de Wit2

1St Francis Hospital, Roslyn, NY, United States, 2DWS Systems, Hoek van Holland, Netherlands

Automatic segmentation of the LV bloodpool using deep learning with a convolutional neural network is a promising, accurate and efficient method for segmentation of cardiac MR images. Although there were a few cases with inaccurate results, "big fails", accuracy is high, R2=0.93 and ejection fraction error ~4%. In the future it may provide a customizable, fast and accurate method for comprehensive evaluation of cardiac MR images.

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.

Click here for more information on becoming a member.

Keywords