Enhanced-QuickDWI: Achieving Equivalent Clinical Quality by Denoising Heavily Sub-sampled Diffusion-Weighted Imaging Data

Whole-body diffusion-weighted imaging (DWI) is a sensitive tool for assessing the spread of metastatic bone malignancies. It offers voxel-wise calculation of apparent diffusion coefficient (ADC) which correlates with tissue cellularity, providing a potential imaging biomarker for tumour response assessment. However, DWI is an inherently noisy technique requiring many signal averages over multiple b-values, leading to times of up to 30 min for a whole-body exam. We present a novel neural network implicitly designed to provide high-quality images from heavily sub-sampled diffusion data (only 1 signal average) which allow whole-body acquisitions of ~ 5 min. We demonstrate that our network can achieve equivalent quality to the clinical b-value and ADC images in a radiological multi-reader study of 100 patients for whole-body and abdomen-pelvis data. We also achieved good agreement to the quantitative values of clinical images within multi-lesion segmentations in 16 patients compared to a previous approach.