Thin-slice T2-weighted images and deep-learning-based super-resolution reconstruction: improved preoperative assessment of vascular invasion for pancreatic ductal adenocarcinoma

Abstract

Abstract Purpose To evaluate the efficacy of thin-slice T2-weighted imaging (T2WI) and super-resolution reconstruction (SRR) for preoperative assessment of vascular invasion in pancreatic ductal adenocarcinoma (PDAC). Methods Ninety-five PDACs with preoperative MRI were retrospectively enrolled as a training set, with non-reconstructed T2WI (NRT2) in different slice thicknesses (NRT2-3, 3 mm; NRT2-5, ≥ 5 mm). A prospective test set was collected with NRT2-5 (n = 125) only. A deep-learning network was employed to generate reconstructed super-resolution T2WI (SRT2) in different slice thicknesses (SRT2-3, 3 mm; SRT2-5, ≥ 5 mm). Image quality was assessed, including the signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and signal-intensity ratio (SIRt/p, tumor/pancreas; SIRt/b, tumor/background). Diagnostic efficacy for vascular invasion was evaluated using the area under the curve (AUC) and compared across different slice thicknesses before and after reconstruction. Results SRT2-5 demonstrated higher SNR and SIRt/p compared to NRT2-5 (74.18 vs 72.46; 1.42 vs 1.30; p < 0.05). SRT2-3 showed increased SIRt/p and SIRt/b over NRT2-3 (1.35 vs 1.31; 2.73 vs 2.58; p < 0.05). SRT2-5 showed higher CNR, SIRt/p and SIRt/b than NRT2-3 (p < 0.05). NRT2-3 outperformed NRT2-5 in evaluating venous invasion (AUC: 0.732 vs 0.597, p = 0.021). SRR improved venous assessment (AUC: NRT2-3, 0.927 vs 0.732; NRT2-5, 0.823 vs 0.597; p < 0.05), and SRT2-5 exhibits comparable efficacy to NRT2-3 in venous assessment (AUC: 0.823 vs 0.732, p = 0.162). Conclusion Thin-slice T2WI and SRR effectively improve the image quality and diagnostic efficacy for assessing venous invasion in PDAC. Thick-slice T2WI with SRR is a potential alternative to thin-slice T2WI. Critical relevance statement Both thin-slice T2-WI and SRR effectively improve image quality and diagnostic performance, providing valuable options for optimizing preoperative vascular assessment in PDAC. Non-invasive and accurate assessment of vascular invasion supports treatment planning and avoids futile surgery. Key Points Vascular invasion evaluation is critical for the surgical eligibility of PDAC. SRR improved image quality and vascular assessment in T2WI. Utilizing thin-slice T2WI and SRR aids in clinical decision making for PDAC. Graphical Abstract

Keywords

• Pancreatic ductal adenocarcinoma
• Vascular invasion
• Super-resolution
• MRI
• T2WI