MRI Extracellular Volume Fraction in Liver Fibrosis-A Comparison of Different Time Points and Blood Pool Measurements.

BACKGROUND: Extracellular volume (ECV) correlates with the degree of liver fibrosis. PURPOSE: To analyze the performance of liver MRI-based ECV evaluations with different blood pool measurements at different time points. STUDY TYPE: Prospective. SAMPLE: 73 consecutive patients (n = 31 females, mean age 56 years) with histopathology-proven liver fibrosis. FIELD STRENGTH/SEQUENCE: 3T acquisition within 90 days of biopsy, including shortened modified look-locker inversion recovery T1 mapping. ASSESSMENT: Polygonal regions of interest were manually drawn in the liver, aorta, vena cava, and in the main, left and right portal vein on four slices before and after Gd-DOTA administration at 5/10/15 minutes. ECV was calculated 1) on one single slice on portal bifurcation level, and 2) averaged over all four slices. STATISTICAL TESTS: Parameters were compared between patients with fibrosis grades F0-2 and F3-F4 with the Mann-Whitney U and fishers exact test. ROC analysis was used to assess the performance of the parameters to predict F3-4 fibrosis. A P-value <0.05 was considered statistically significant. RESULTS: ECV was significantly higher in F3-4 fibrosis (35.4% [33.1%-37.6%], 36.1% [34.2%-37.5%], and 37.0% [34.8%-39.2%] at 5/10/15 minutes) than in patients with F0-2 fibrosis (33.3% [30.8%-34.8%], 33.7% [31.6%-34.7%] and 34.9% [32.2%-36.0%]; AUC = 0.72-0.75). Blood pool T1 relaxation times in the aorta and vena cava were longer on the upper vs. lower slices at 5 minutes, but not at 10/15 minutes. AUC values were similar when measured on a single slice (AUC = 0.69-0.72) or based on blood pool measurements in the cava or portal vein (AUC = 0.63-0.67 and AUC = 0.65-0.70). DATA CONCLUSION: Liver ECV is significantly higher in F3-4 fibrosis compared to F0-2 fibrosis with blood pool measurements performed in the aorta, inferior vena cava, and portal vein at 5, 10, and 15 minutes. However, a smaller variability was observed for blood pool measurements between slices at 15 minutes. LEVEL OF EVIDENCE: 1 TECHNICAL EFFICACY: Stage 3.

Automated liver segmental volume ratio quantification on non-contrast T1-Vibe Dixon liver MRI using deep learning.

PURPOSE: To evaluate the effectiveness of automated liver segmental volume quantification and calculation of the liver segmental volume ratio (LSVR) on a non-contrast T1-vibe Dixon liver MRI sequence using a deep learning segmentation pipeline. METHOD: A dataset of 200 liver MRI with a non-contrast 3 mm T1-vibe Dixon sequence was manually labeledslice-by-sliceby an expert for Couinaud liver segments, while portal and hepatic veins were labeled separately. A convolutional neural networkwas trainedusing 170 liver MRI for training and 30 for evaluation. Liver segmental volumes without liver vessels were retrieved and LSVR was calculated as the liver segmental volumes I-III divided by the liver segmental volumes IV-VIII. LSVR was compared with the expert manual LSVR calculation and the LSVR calculated on CT scans in 30 patients with CT and MRI within 6 months. RESULTS: Theconvolutional neural networkclassified the Couinaud segments I-VIII with an average Dice score of 0.770 ± 0.03, ranging between 0.726 ± 0.13 (segment IVb) and 0.810 ± 0.09 (segment V). The calculated mean LSVR with liver MRI unseen by the model was 0.32 ± 0.14, as compared with manually quantified LSVR of 0.33 ± 0.15, resulting in a mean absolute error (MAE) of 0.02. A comparable LSVR of 0.35 ± 0.14 with a MAE of 0.04 resulted with the LSRV retrieved from the CT scans. The automated LSVR showed significant correlation with the manual MRI LSVR (Spearman r = 0.97, p < 0.001) and CT LSVR (Spearman r = 0.95, p < 0.001). CONCLUSIONS: A convolutional neural network allowed for accurate automated liver segmental volume quantification and calculation of LSVR based on a non-contrast T1-vibe Dixon sequence.

Convolutional neural network for automated segmentation of the liver and its vessels on non-contrast T1 vibe Dixon acquisitions.

We evaluated the effectiveness of automated segmentation of the liver and its vessels with a convolutional neural network on non-contrast T1 vibe Dixon acquisitions. A dataset of non-contrast T1 vibe Dixon liver magnetic resonance images was labelled slice-by-slice for the outer liver border, portal, and hepatic veins by an expert. A 3D U-Net convolutional neural network was trained with different combinations of Dixon in-phase, opposed-phase, water, and fat reconstructions. The neural network trained with the single-modal in-phase reconstructions achieved a high performance for liver parenchyma (Dice 0.936 ± 0.02), portal veins (0.634 ± 0.09), and hepatic veins (0.532 ± 0.12) segmentation. No benefit of using multi-modal input was observed (p = 1.0 for all experiments), combining in-phase, opposed-phase, fat, and water reconstruction. Accuracy for differentiation between portal and hepatic veins was 99% for portal veins and 97% for hepatic veins in the central region and slightly lower in the peripheral region (91% for portal veins, 80% for hepatic veins). In conclusion, deep learning-based automated segmentation of the liver and its vessels on non-contrast T1 vibe Dixon was highly effective. The single-modal in-phase input achieved the best performance in segmentation and differentiation between portal and hepatic veins.