Automated liver and spleen segmentation for MR elastography maps using U-Nets

• Published in: Scientific reports Vol. 15; no. 1; pp. 10762 - 12
• Main Authors: Jaitner, Noah, Ludwig, Jakob, Meyer, Tom, Boehm, Oliver, Anders, Matthias, Huang, Biru, Jordan, Jakob, Schaeffter, Tobias, Sack, Ingolf, Reiter, Rolf
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 28.03.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 692/308; 692/4020; 692/53; 692/700/1421; 692/700/1421/1628; Adult; Automation; Correlation analysis; Correlation coefficient; Elasticity Imaging Techniques - methods; Female; Humanities and Social Sciences; Humans; Image processing; Image Processing, Computer-Assisted - methods; Liver; Liver - diagnostic imaging; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Middle Aged; multidisciplinary; Science; Science (multidisciplinary); Segmentation; Spleen; Spleen - diagnostic imaging; Statistical analysis; Young Adult
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-025-95157-w

To compare pretrained and trained U-Nets for liver and spleen segmentation in multifrequency magnetic resonance elastography (MRE) magnitude images for automated quantification of shear wave speed (SWS). Seventy-two healthy participants (34 ± 11 years; BMI, 23 ± 2 kg/m 2 ; 51 men) underwent multifrequency MRE at 1.5T or 3T. Volumes of interest (VOIs) of liver and spleen were generated from MRE magnitude images with mixed T2-T2* image contrast and then transferred to SWS maps. Pretrained and trained 2D and 3D U-Nets were compared with ground truth values obtained by manual segmentation using correlation analysis, intraclass correlation coefficients (ICCs), and Dice scores. For both VOI and SWS values, pairwise comparison revealed no statistically significant difference between ground truth and pretrained and trained U-Nets (all p  ≥ 0.95). There was a strong positive correlation for SWS between ground truth and U-Nets with R  = 0.99 for liver and R  = 0.81–0.84 for spleen. ICC was 0.99 for liver and 0.90–0.92 for spleen, indicating excellent agreement for liver and good agreement for spleen for all U-Nets investigated. Dice scores showed excellent segmentation performance for all networks with the 2D U-Net achieving slightly higher values for the liver (0.95) and spleen (0.90), though the differences between the three tested U-Nets were minimal. The excellent performance we found for automated liver and spleen segmentation when applying 2D and 3D U-Nets to MRE magnitude images suggests that fully automated quantification of MRE parameters within anatomical regions is feasible by leveraging the previously unexploited anatomical information conveyed in MRE magnitude images.