We have located links that may give you full text access.
Unsupervised Denoising and Super-Resolution of Vascular Flow Data by Physics-informed Machine Learning.
Journal of Biomechanical Engineering 2024 March 27
PURPOSE: We present an unsupervised deep learning method to perform flow denoising and super-resolution without high resolution labels. We demonstrate the ability of this model to reconstruct 3D stenosis and aneurysm flows, with varying geometries, orientations, and boundary conditions.
METHODS: Ground truth data was generated using computational fluid dynamics, and then corrupted with multiplicative Gaussian noise. Autoencoders were used to compress the representations of the flow domain geometry and the (possibly noisy and low-resolution) flow field. These representations were used to condition a physics-informed neural network. A physics-based loss was implemented to train the model to recover lost information from the noisy input by transforming the flow to a solution of the Navier-Stokes equations.
RESULTS: Our experiments achieved mean squared errors in the true flow reconstruction of order 1.0e-4, and root mean squared residuals of order 1.0e-2 for the momentum and continuity equations. Our method yielded correlation coefficients of 0.971 for the pressure field and 0.82 for the wall shear stress magnitude field.
CONCLUSION: By performing point-wise predictions of the flow, the model was able to robustly denoise and super-resolve the field to 20x the input resolution.
METHODS: Ground truth data was generated using computational fluid dynamics, and then corrupted with multiplicative Gaussian noise. Autoencoders were used to compress the representations of the flow domain geometry and the (possibly noisy and low-resolution) flow field. These representations were used to condition a physics-informed neural network. A physics-based loss was implemented to train the model to recover lost information from the noisy input by transforming the flow to a solution of the Navier-Stokes equations.
RESULTS: Our experiments achieved mean squared errors in the true flow reconstruction of order 1.0e-4, and root mean squared residuals of order 1.0e-2 for the momentum and continuity equations. Our method yielded correlation coefficients of 0.971 for the pressure field and 0.82 for the wall shear stress magnitude field.
CONCLUSION: By performing point-wise predictions of the flow, the model was able to robustly denoise and super-resolve the field to 20x the input resolution.
Full text links
Related Resources
Trending Papers
A Guide to the Use of Vasopressors and Inotropes for Patients in Shock.Journal of Intensive Care Medicine 2024 April 14
Prevention and treatment of ischaemic and haemorrhagic stroke in people with diabetes mellitus: a focus on glucose control and comorbidities.Diabetologia 2024 April 17
British Society for Rheumatology guideline on management of adult and juvenile onset Sjögren disease.Rheumatology 2024 April 17
Diagnosis and Management of Cardiac Sarcoidosis: A Scientific Statement From the American Heart Association.Circulation 2024 April 19
Albumin: a comprehensive review and practical guideline for clinical use.European Journal of Clinical Pharmacology 2024 April 13
Eosinophilic Esophagitis: Clinical Pearls for Primary Care Providers and Gastroenterologists.Mayo Clinic Proceedings 2024 April
Get seemless 1-tap access through your institution/university
For the best experience, use the Read mobile app
All material on this website is protected by copyright, Copyright © 1994-2024 by WebMD LLC.
This website also contains material copyrighted by 3rd parties.
By using this service, you agree to our terms of use and privacy policy.
Your Privacy Choices
You can now claim free CME credits for this literature searchClaim now
Get seemless 1-tap access through your institution/university
For the best experience, use the Read mobile app