Meeting Banner
Abstract #4763

Automatic detection of corrupted frames in cardiac DTI with machine learning

Francesca Cavallo1, Pedro Ferreira1, Zohya Khalique1, Andrew Scott1, Sonia Nielles-Vallespin2, and David Firmin1

1Cardiovascular BRU, Royal Brompton Hospital, London, United Kingdom, 2NHLBI, National Institutes of Health, MD, United States

In vivo cardiac DTI is capable of probing the microstructure of the myocardium and its dynamics throughout the cardiac cycle. The typical cardiac DTI scan data will contain corrupted frames due to cardiac and respiratory motion. Currently an experienced observer identifies corrupted frames by means of a visual assessment and manually removes them. In this work we show that machine learning can be used to accurately assess DTI corrupted frames, reducing the user input, accelerating analysis and removing human subjectivity.

This abstract and the presentation materials are available to members only; a login is required.

Join Here