Feasibility of automated 3-dimensional magnetic resonance imaging pancreas segmentation

Abstract

Purpose: With the advent of magnetic resonance imaging (MRI) guided radiation therapy, internal organ motion can be imaged simultaneously during treatment. In this study, we evaluate the feasibility of pancreas MRI segmentation using state-of-the-art segmentation methods. Methods and materials: T2-weighted half-Fourier acquisition single-shot turbo spin-echo and T1 weighted volumetric interpolated breath-hold examination images were acquired on 3 patients and 2 healthy volunteers for a total of 12 imaging volumes. A novel dictionary learning (DL) method was used to segment the pancreas and compared to t mean-shift merging, distance regularized level set, and graph cuts, and the segmentation results were compared with manual contours using Dice's index, Hausdorff distance, and shift of the center of the organ (SHIFT). Results: All volumetric interpolated breath-hold examination images were successfully segmented by at least 1 of the autosegmentation method with Dice's index >0.83 and SHIFT ≤2 mm using the best automated segmentation method. The automated segmentation error of half-Fourier acquisition single-shot turbo spin-echo images was significantly greater. DL is statistically superior to the other methods in Dice’s overlapping index. For the Hausdorff distance and SHIFT measurement, distance regularized level set and DL performed slightly superior to the graph cuts method, and substantially superior to mean-shift merging. DL required least human supervision and was faster to compute. Conclusions: Our study demonstrated potential feasibility of automated segmentation of the pancreas on MRI scans with minimal human supervision at the beginning of imaging acquisition. The achieved accuracy is promising for organ localization.