Meeting Banner
Abstract #1047

Automatic AHA model segmentation of cardiac T1 maps with deep learning

Nicola Martini1, Daniele Della Latta1, Gianmarco Santini1,2, Gabriele Valvano1, Andrea Barison3, Francesco Avogliero1, Daniele De Marchi3, Luigi Landini1,2, and Dante Chiappino1

1Fondazione Toscana "G. Monasterio", Massa, Italy, 2University of Pisa, Pisa, Italy, 3Fondazione Toscana "G. Monasterio", Pisa, Italy

We proposed a fully automated approach for the segmental analysis of T1 mapping using a fully convolutional neural network architecture. T1 maps acquired using the MOLLI sequence from 394 subjects were considered. Excellent segmentation results are demonstrated by high Jaccard (0.969±0.023) and a Dice (0.984±0.012) indexes. No significant difference in the obtained segmental T1 values compared to manual measurements was found, with a mismatch percentage ranging from 0.95% to 3.14% across segments.

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

Join Here