The impact of segmentation on whole-lung functional MRI quantification: Repeatability and reproducibility from multiple human observers and an artificial neural network.

CONCLUSIONS: Despite high overall agreement, there were systematic differences in lung segmentation between observers. This needs to be considered for longitudinal studies and could be overcome by using an ANN, which performs as good as human observers and fully automatizes MP-MRI post-processing. PMID: 32892445 [PubMed - as supplied by publisher]

https://www.ncbi.nlm.nih.gov/pubmed/32892445?dopt=Abstract

Source: Magnetic Resonance in Medicine - September 5, 2020 Category: Radiology Authors: Willers C, Bauman G, Andermatt S, Santini F, Sandkühler R, Ramsey KA, Cattin PC, Bieri O, Pusterla O, Latzin P Tags: Magn Reson Med Source Type: research