Automated Measurement of Pancreatic Fat Deposition on Dixon MRI Using nnU‐Net
Authors:
- 30 May 2022
- journal article
- research article
- Published by Wiley in Journal of Magnetic Resonance Imaging
- Vol. 57 (1) , 296-307
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: 3Technical Efficacy: Stage 3Keywords
This publication has 31 references indexed in Scilit:
- Hepatic MR imaging for in vivo differentiation of steatosis, iron deposition and combined storage disorder: Single-ratio in/opposed phase analysis vs. dual-ratio Dixon discriminationEuropean Journal of Radiology, 2012
- The worldwide epidemiology of type 2 diabetes mellitus—present and future perspectivesNature Reviews Endocrinology, 2011
- Lipids in the Wrong Place: Visceral Fat and Nonalcoholic SteatohepatitisDiabetes Care, 2011
- Pancreatic fat is negatively associated with insulin secretion in individuals with impaired fasting glucose and/or impaired glucose tolerance: a nuclear magnetic resonance studyDiabetes/Metabolism Research and Reviews, 2010
- A Mouse Model of Metabolic Syndrome: Insulin Resistance, Fatty Liver and Non-Alcoholic Fatty Pancreas Disease (NAFPD) in C57BL/6 Mice Fed a High Fat DietJournal of Clinical Biochemistry and Nutrition, 2010
- Quantification of Pancreatic Lipomatosis and Liver Steatosis by MRI: Comparison of In/Opposed-Phase and Spectral-Spatial Excitation TechniquesInvestigative Radiology, 2008
- User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliabilityNeuroImage, 2006
- A fast spin echo two-point Dixon technique and its combination with sensitivity encoding for efficient T2-weighted imagingMagnetic Resonance Imaging, 2005
- Breath‐hold water and fat imaging using a dual‐echo two‐point dixon technique with an efficient and robust phase‐correction algorithmMagnetic Resonance in Medicine, 2004
- Anatomicosurgical segments of the human pancreasSurgical and Radiologic Anatomy, 1988