Deep-learned estimation of uncertainty in measurements of apparent diffusion coefficient from whole-body diffusion-weighted MRI. (October 2022)

• Record Type: Journal Article
• Authors: Zormpas-Petridis, Konstantinos; Tunariu, Nina; Collins, David J.; Messiou, Christina; Koh, Dow-Mu; Blackledge, Matthew D.
• Is Part Of: Computers in biology and medicine. Volume 149(2022)
• Publication Date: 2022-10
• Subjects: Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.106091
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Purpose: To use deep learning to calculate the uncertainty in apparent diffusion coefficient (σADC) voxel-wise measurements to clinically impact the monitoring of treatment response and improve the quality of ADC maps. Materials and methods: We use a uniquely designed diffusion-weighted imaging (DWI) acquisition protocol that provides gold-standard measurements of σADC to train a deep learning model on two separate cohorts: 16 patients with prostate cancer and 28 patients with mesothelioma. Our network was trained with a novel cost function, which incorporates a perception metric and a b-value regularisation term, on ADC maps calculated by combinations of 2 or 3 b-values (e.g. 50/600/900, 50/900, 50/600, 600/900 s/mm 2 ). We compare the accuracy of the deep-learning based approach for estimation of σADC with gold-standard measurements. Results: The model accurately predicted the σADC for every b-value combination in both cohorts. Mean values of σADC within areas of active disease deviated from those measured by the gold-standard by 4.3% (range, 2.87–6.13%) for the prostate and 3.7% (range, 3.06–4.54%) for the mesothelioma cohort. We also showed that the model can easily be adapted for a different DWI protocol and field-of-view with only a few images (as little as a single patient) using transfer learning. Conclusion: Deep learning produces maps of σADC from standard clinical diffusion-weighted images (DWI) when 2 or more b-values are available. Highlights: Deep learning can robustly calculate maps of pixel-wise uncertainty in ADC estimation of diffusion-weighted MRI (DWI). Breaks conventional understanding that estimates of uncertainty cannot be calculated using 2-point linear fitting. Demonstrate the utility of deep-learned ADC uncertainty mapping in whole-body MRI and smaller field-of-view lung imaging. A novel b-value regularisation term of the training loss function increases the network's performance. Our method can be used in clinical DWI protocols, without the need to alter the DWI protocol.