Meeting Banner
Abstract #2179

Quality prediction score: predicting the CNN-based segmentation performance for cine cardiac MR images

Ping-Chen Wu1, Zheng-Shen Lin1, and Teng-Yi Huang1
1Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan

In this study, we evaluated the open-source toolbox for heart segmentation by using cross-institutional datasets. Furthermore, we proposed to use a quality prediction socre to provide the estimation of the qualitfy of the cardiac segmentation. The QPS values were highly correlated to the Dice coefficients of the test datasets.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here