Deep learning reconstruction accelerated reduced field-of-view DWI in rectal cancer: mucosa-submucosa-muscularis visualization and T staging

TL;DR

Deep learning reconstruction improved image quality and staging accuracy for rectal cancer in MRI scans, especially for early-stage tumors.

Contribution

DLR applied to reduced field-of-view DWI improves visualization and T-staging accuracy in rectal cancer.

Findings

rFOVDL DWI reduced acquisition time by 30% compared to fFOVSTA DWI.

rFOVDL DWI outperformed fFOVSTA in qualitative image quality and T-staging accuracy, especially for early-stage tumors.

Higher inter-reader agreement was observed with rFOVDL DWI for staging and ADC measurements.

Abstract

We compared the image quality and diagnostic performance of deep learning reconstruction (DLR) accelerated reduced field-of-view (rFOVDL) diffusion-weighted imaging (DWI) with standard-reconstructed full field-of-view (fFOVSTA) DWI in rectal cancer.

This prospective study enrolled 173 participants with biopsy-confirmed rectal adenocarcinoma from November 2022 to August 2023 undergoing rFOVDL and fFOVSTA DWI scans. Two radiologists evaluated qualitative image quality, objective image quality, and apparent diffusion coefficient (ADC) independently. T and N staging were evaluated in 94 participants undergoing radical surgery. Diagnostic sensitivity, specificity, and accuracy were calculated using histopathologic results as the gold standard. ADC values were analyzed for correlations with histopathologic staging.

We observed that rFOVDL DWI reduced acquisition time by 30% compared to fFOVSTA DWI. rFOVDL DWI outperformed fFOVSTA DWI in all qualitative image quality metrics (p ≤ 0.013), especially in mucosa-submucosa-muscularis visualization, spatial resolution, overall image quality, and diagnostic confidence, accompanied by comparable objective image quality (p ≥ 0.054). When applied with T2-weighted imaging, rFOVDL DWI significantly enhanced primary T-staging accuracy than fFOVSTA DWI (p < 0.001), especially for early-stage tumors (T1 or T2). Tumor ADC values of rFOVDL DWI were lower than those of fFOVSTA DWI, yet remained solid inverse correlations with histopathologic T-staging (p < 0.001). Higher inter-reader agreements of locoregional staging and ADC measurements were obtained by rFOVDL DWI.

rFOVDL DWI significantly improved image quality than fFOVSTA DWI, with a 30% reduced acquisition time. rFOVDL DWI facilitated higher primary T-staging accuracy, especially for early-stage rectal cancer (T1–T2).

Reduced acquisition time and improved imaging quality highlighted the clinical feasibility of applying DLR to rFOV DWI. rFOVDL DWI could significantly enhance primary T-staging accuracy, especially for early-stage rectal cancer (T1–T2), facilitating more precise treatment management.

Applying deep learning reconstruction (DLR) to reduced field-of-view (rFOV) diffusion-weighted imaging (DWI) improved mucosa-submucosa-muscularis visualization and reduced acquisition time.DLR-based rFOV DWI significantly enhanced primary T-staging accuracy for rectal cancer, especially for early-stage tumors (T1 or T2).DLR-based rFOV DWI facilitated higher inter-reader agreements for locoregional staging and apparent diffusion coefficient measurement in rectal cancer.

Applying deep learning reconstruction (DLR) to reduced field-of-view (rFOV) diffusion-weighted imaging (DWI) improved mucosa-submucosa-muscularis visualization and reduced acquisition time.

DLR-based rFOV DWI significantly enhanced primary T-staging accuracy for rectal cancer, especially for early-stage tumors (T1 or T2).

DLR-based rFOV DWI facilitated higher inter-reader agreements for locoregional staging and apparent diffusion coefficient measurement in rectal cancer.

Figures