Automated Measurement of Pancreatic Fat Deposition on Dixon MRI Using nnU-Net

Abstract

Background: Pancreatic fat accumulation may cause or aggravate the process of acute pancreatitis, β-cell dysfunction, T2DM disease, and even be associated with pancreatic tumors. The pathophysiology of fatty pancreas remains overlooked and lacks effective imaging diagnostics.

Purpose: To automatically measure the distribution of pancreatic fat deposition on Dixon MRI in multicenter/population datasets using nnU-Net models.

Study type: Retrospective.

Population: A total of 176 obese/nonobese subjects (90 males, 86 females; mean age, 27.2 ± 19.7) were enrolled, including a training set (N = 132) and a testing set (N = 44).

Field strength/sequence: A 3 T and 1.5 T/gradient echo T₁ dual-echo Dixon.

Assessment: The segmentation results of four types of nnU-Net models were compared using dice similarity coefficient (DSC), positive predicted value (PPV), and sensitivity. The ground truth was the manual delineation by two radiologists according to in-phase (IP) and opposed-phase (OP) images.

Statistical tests: The group difference of segmentation results of four models were assessed by the Kruskal-Wallis H test with Dunn-Bonferroni comparisons. The interobserver agreement of pancreatic fat fraction measurements across three observers and test-retest reliability of human and machine were assessed by intragroup correlation coefficient (ICC). P < 0.05 was considered statistically significant.

Results: The three-dimensional (3D) dual-contrast model had significantly improved performance than 2D dual-contrast (DSC/sensitivity) and 3D one-contrast (IP) models (DSC/PPV/sensitivity) and had less errors than 3D one-contrast (OP) model according to higher DSC and PPV (not significant), with a mean DSC of 0.9158, PPV of 0.9105 and sensitivity of 0.9232 in the testing set. The test-retest ICC of this model was above 0.900 in all pancreatic regions, exceeded human.

Data conclusion: 3D Dual-contrast nnU-Net aided segmentation of pancreas on Dixon images appears to be adaptable to multicenter/population datasets. It fully automates the assessment of pancreatic fat distribution and has high reliability.

Evidence level: 3 TECHNICAL EFFICACY: Stage 3.

Keywords: T2DM; deep learning; ectopic fat deposition; fat quantification; nnU-Net; pancreas.