Meeting Banner
Abstract #2981

Automatic bullseye analysis of myocardial T1 values: a segmentation approach based on deep learning

Yu-Nian Ou1, Tsai-Ling Yang1, Teng-Yi Huang1, and Ming-Ting Wu2

1Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 2Department of Radiology, Kao-Hsiung Veterans General Hospital, Kao-Hsiung, Taiwan

The study presents an automatic segmentation method for short-axis MOLLI data sets. We used a deep learning method based on convolutional neural network to accurately extract walls and blood pool regions of left and right ventricle. We compared the results with a layer-growing method presented in ISMRM 2017 and found that the accuracy of segmentation was significantly improved when using the deep learning method.

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

Join Here