|
|
For actual-time CMR beneath exercise stress, nnU-Net achieves Dice’s coefficients of 0.92 for LV, 0.Eighty five for MYO, and 0.83 for RV and the mean absolute variations between nnU-Net and reference are 11.Four mL for EDV, 2.9 mL for ESV and 3.6 % for EF. For nnU-Net, the absolute and relative variations of EDV, ESV, and EF are less than the inter-observer variability, although the direct comparability is restricted as a result of images have been newly selected for intra- and inter-observer variability, whereas the nnU-Net segmentation has been compared to the manually corrected contours of the same photos. For actual-time CMR at relaxation, nnU-Net achieves Dice’s coefficients of 0.94 for LV, 0.89 for MYO, and 0.Ninety for RV and the imply absolute differences between nnU-Net and the reference are 2.9 mL for EDV, 3.5 mL for ESV and 2.6 % for EF. Consequently, the 2D version of nnU-Net with weights pre-trained on the ACDC dataset was applied on single photos of the dataset for all cine and actual-time measurements.
Stop by my webpage - https://mitolyns.net |
|