Accelerating Whole-Body Diffusion-weighted MRI with Deep Learning-based Denoising Image Filters

Konstantinos Zormpas-Petridis; Nina Tunariu; Andra Curcean; Christina Messiou; Sebastian Curcean; David J Collins; Julie C Hughes; Yann Jamin; Dow-Mu Koh; Matthew D Blackledge

doi:10.1148/ryai.2021200279

Accelerating Whole-Body Diffusion-weighted MRI with Deep Learning-based Denoising Image Filters

Radiol Artif Intell. 2021 Jul 14;3(5):e200279. doi: 10.1148/ryai.2021200279. eCollection 2021 Sep.

Affiliation

¹ Division of Radiation Therapy and Imaging, The Institute of Cancer Research, 123 Old Brompton Rd, London SW7 3RP, England (K.Z.P., N.T., A.C., C.M., S.C., D.J.C., J.C.H., Y.J., D.M.K., M.D.B.); and Department of Radiology, The Royal Marsden National Health Service Foundation Trust, Surrey, England (N.T., A.C., C.M., S.C., J.C.H., D.M.K.).

Abstract

Purpose: To use deep learning to improve the image quality of subsampled images (number of acquisitions = 1 [NOA₁]) to reduce whole-body diffusion-weighted MRI (WBDWI) acquisition times.

Materials and methods: Both retrospective and prospective patient groups were used to develop a deep learning-based denoising image filter (DNIF) model. For initial model training and validation, 17 patients with metastatic prostate cancer with acquired WBDWI NOA₁ and NOA₉ images (acquisition period, 2015-2017) were retrospectively included. An additional 22 prospective patients with advanced prostate cancer, myeloma, and advanced breast cancer were used for model testing (2019), and the radiologic quality of DNIF-processed NOA₁ (NOA_1-DNIF) images were compared with NOA₁ images and clinical NOA₁₆ images by using a three-point Likert scale (good, average, or poor; statistical significance was calculated by using a Wilcoxon signed ranked test). The model was also retrained and tested in 28 patients with malignant pleural mesothelioma (MPM) who underwent lung MRI (2015-2017) to demonstrate feasibility in other body regions.

Results: The model visually improved the quality of NOA₁ images in all test patients, with the majority of NOA_1-DNIF and NOA₁₆ images being graded as either "average" or "good" across all image-quality criteria. From validation data, the mean apparent diffusion coefficient (ADC) values within NOA_1-DNIF images of bone disease deviated from those within NOA₉ images by an average of 1.9% (range, 1.1%-2.6%). The model was also successfully applied in the context of MPM; the mean ADCs from NOA_1-DNIF images of MPM deviated from those measured by using clinical-standard images (NOA₁₂) by 3.7% (range, 0.2%-10.6%).

Conclusion: Clinical-standard images were generated from subsampled images by using a DNIF.Keywords: Image Postprocessing, MR-Diffusion-weighted Imaging, Neural Networks, Oncology, Whole-Body Imaging, Supervised Learning, MR-Functional Imaging, Metastases, Prostate, Lung Supplemental material is available for this article. Published under a CC BY 4.0 license.

Keywords: Image Postprocessing; Lung; MR-Diffusion-weighted Imaging; MR-Functional Imaging; Metastases; Neural Networks; Oncology; Prostate; Supervised Learning; Whole-Body Imaging.

2021 by the Radiological Society of North America, Inc.