Strotzer, Quirin David and Winther, Hinrich and Utpatel, Kirsten and Scheiter, Alexander and Fellner, Claudia and Doppler, Michael Christian and Ringe, Kristina Imeen and Raab, Florian and Haimerl, Michael and Uller, Wibke and Stroszczynski, Christian and Luerken, Lukas and Verloh, Niklas (2022) Application of A U-Net for Map-like Segmentation and Classification of Discontinuous Fibrosis Distribution in Gd-EOB-DTPA-Enhanced Liver MRI. DIAGNOSTICS, 12 (8): 1938. ISSN , 2075-4418
Full text not available from this repository. (Request a copy)Abstract
We aimed to evaluate whether U-shaped convolutional neuronal networks can be used to segment liver parenchyma and indicate the degree of liver fibrosis/cirrhosis at the voxel level using contrast-enhanced magnetic resonance imaging. This retrospective study included 112 examinations with histologically determined liver fibrosis/cirrhosis grade (Ishak score) as the ground truth. The T1-weighted volume-interpolated breath-hold examination sequences of native, arterial, late arterial, portal venous, and hepatobiliary phases were semi-automatically segmented and co-registered. The segmentations were assigned the corresponding Ishak score. In a nested cross-validation procedure, five models of a convolutional neural network with U-Net architecture (nnU-Net) were trained, with the dataset being divided into stratified training/validation (n = 89/90) and holdout test datasets (n = 23/22). The trained models precisely segmented the test data (mean dice similarity coefficient = 0.938) and assigned separate fibrosis scores to each voxel, allowing localization-dependent determination of the degree of fibrosis. The per voxel results were evaluated by the histologically determined fibrosis score. The micro-average area under the receiver operating characteristic curve of this seven-class classification problem (Ishak score 0 to 6) was 0.752 for the test data. The topthree-accuracy-score was 0.750. We conclude that determining fibrosis grade or cirrhosis based on multiphase Gd-EOB-DTPA-enhanced liver MRI seems feasible using a 2D U-Net. Prospective studies with localized biopsies are needed to evaluate the reliability of this model in a clinical setting.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | HEPATOBILIARY PHASE; SAMPLING VARIABILITY; SIGNAL INTENSITY; CONTRAST AGENT; REMNANT LIVER; ELASTOGRAPHY; BIOPSY; PREDICTION; VOLUME; liver fibrosis; cirrhosis; segmentation; Artificial Intelligence; U-Net; convolutional neural network |
| Subjects: | 600 Technology > 610 Medical sciences Medicine |
| Divisions: | Medicine > Lehrstuhl für Pathologie Medicine > Lehrstuhl für Röntgendiagnostik |
| Depositing User: | Dr. Gernot Deinzer |
| Date Deposited: | 13 Feb 2024 10:26 |
| Last Modified: | 13 Feb 2024 10:26 |
| URI: | https://pred.uni-regensburg.de/id/eprint/57164 |
Actions (login required)
 |
View Item |
