Utility of Thin-slice Fat-suppressed Single-shot T2-weighted MR Imaging with Deep Learning Image Reconstruction as a Protocol for Evaluating the Pancreas

Abstract

Purpose: To compare the utility of thin-slice fat-suppressed single-shot T2-weighted imaging (T2WI) with deep learning image reconstruction (DLIR) and conventional fast spin-echo T2WI with DLIR for evaluating pancreatic protocol.

Methods: This retrospective study included 42 patients (mean age, 70.2 years) with pancreatic cancer who underwent gadoxetic acid-enhanced MRI. Three fat-suppressed T2WI, including conventional fast-spin echo with 6 mm thickness (FSE 6 mm), single-shot fast-spin echo with 6 mm and 3 mm thickness (SSFSE 6 mm and SSFSE 3 mm), were acquired for each patient. For quantitative analysis, the SNRs of the upper abdominal organs were calculated between images with and without DLIR. The pancreas-to-lesion contrast on DLIR images was also calculated. For qualitative analysis, two abdominal radiologists independently scored the image quality on a 5-point scale in the FSE 6 mm, SSFSE 6 mm, and SSFSE 3 mm with DLIR.

Results: The SNRs significantly improved among the three T2-weighted images with DLIR compared to those without DLIR in all patients (P < 0.001). The pancreas-to-lesion contrast of SSFSE 3 mm was higher than those of the FSE 6 mm (P < 0.001) and tended to be higher than SSFSE 6 mm (P = 0.07). SSFSE 3 mm had the highest image qualities regarding pancreas edge sharpness, pancreatic duct clarity, and overall image quality, followed by SSFSE 6 mm and FSE 6 mm (P < 0.0001).

Conclusion: SSFSE 3 mm with DLIR demonstrated significant improvements in SNRs of the pancreas, pancreas-to-lesion contrast, and image quality more efficiently than did SSFSE 6 mm and FSE 6 mm. Thin-slice fat-suppressed single-shot T2WI with DLIR can be easily implemented for pancreatic MR protocol.

Keywords: T2-weighted; artificial intelligence; magnetic resonance imaging; pancreas.

Fig. 1

ROI placements on SSFSE 3 mm images without (A, C) and with (B, D) DLIR algorithm. ROIs are manually drawn on the liver, pancreas, pancreatic cancer, paraspinal muscle, and intra-abdominal fat (circles). DLIR, deep learning image reconstruction; SSFSE, single-shot fast-spin echo.

Fig. 2

Axial T2-weighted images in a 68-year-old man with pancreatic ductal adenocarcinoma of the pancreas head. DLIR reduces image noise among (B) FSE 6 mm, (D) SSFSE 6 mm, and (F) SSFSE 3 mm compared with (A) FSE 6 mm, (C) SSFSE 6 mm, and (E) SSFSE 3 mm without implementation of DLIR. The main pancreatic duct is more clearly visualized, and pancreas edge sharpness is more evident on SSFSE 3 mm with DLIR than on FSE 6 mm with DLIR and SSFSE 6 mm with DLIR. DLIR, deep learning image reconstruction; FSE, fast-spin echo; SSFSE, single-shot fast-spin echo.

Fig. 3

Box plots showing pancreas-to-lesion contrast on the FSE 6 mm, SSFSE 6 mm, and SSFSE 3 mm images with DLIR. The lower boundary of the boxes indicates the 25th percentile, the line within the boxes indicates the median, and the higher boundary of the boxes indicates the 75th percentile. DLIR, deep learning image reconstruction; FSE, fast-spin echo; SSFSE, single-shot fast-spin echo.

Fig. 4

Axial T2-weighted images in a 73-year-old man with pancreatic ductal adenocarcinoma of the pancreas head (not depicted in these slices). Substantial motion artifacts from the gastrointestinal tract deteriorate image quality on (A) FSE 6 mm with DLIR. A decrease in the motion artifacts improves visualization of the pancreas on (B) SSFSE 6 mm and (C) SSFSE 3 mm with DLIR. DLIR, deep learning image reconstruction; FSE, fast-spin echo; SSFSE, single-shot fast-spin echo.