More Like this

1. Coherent plug-and-play artifact removal: Physics-based deep learning for imaging through aberrations

   https://doi.org/10.1016/j.optlaseng.2023.107496  

   Pellizzari, Casey J.; Bate, Timothy J.; Donnelly, Kevin P.; Buzzard, Gregery T.; Bouman, Charles A.; Spencer, Mark F. (May 2023, Optics and Lasers in Engineering)
2. Multi‐mask self‐supervised learning for physics‐guided neural networks in highly accelerated magnetic resonance imaging

   https://doi.org/10.1002/nbm.4798  

   Yaman, Burhaneddin; Gu, Hongyi; Hosseini, Seyed Amir; Demirel, Omer Burak; Moeller, Steen; Ellermann, Jutta; Uğurbil, Kâmil; Akçakaya, Mehmet (December 2022, NMR in Biomedicine)

   Self‐supervised learning has shown great promise because of its ability to train deep learning (DL) magnetic resonance imaging (MRI) reconstruction methods without fully sampled data. Current self‐supervised learning methods for physics‐guided reconstruction networks split acquired undersampled data into two disjoint sets, where one is used for data consistency (DC) in the unrolled network, while the other is used to define the training loss. In this study, we propose an improved self‐supervised learning strategy that more efficiently uses the acquired data to train a physics‐guided reconstruction network without a database of fully sampled data. The proposed multi‐mask self‐supervised learning via data undersampling (SSDU) applies a holdout masking operation on the acquired measurements to split them into multiple pairs of disjoint sets for each training sample, while using one of these pairs for DC units and the other for defining loss, thereby more efficiently using the undersampled data. Multi‐mask SSDU is applied on fully sampled 3D knee and prospectively undersampled 3D brain MRI datasets, for various acceleration rates and patterns, and compared with the parallel imaging method, CG‐SENSE, and single‐mask SSDU DL‐MRI, as well as supervised DL‐MRI when fully sampled data are available. The results on knee MRI show that the proposed multi‐mask SSDU outperforms SSDU and performs as well as supervised DL‐MRI. A clinical reader study further ranks the multi‐mask SSDU higher than supervised DL‐MRI in terms of signal‐to‐noise ratio and aliasing artifacts. Results on brain MRI show that multi‐mask SSDU achieves better reconstruction quality compared with SSDU. The reader study demonstrates that multi‐mask SSDU at R = 8 significantly improves reconstruction compared with single‐mask SSDU at R = 8, as well as CG‐SENSE at R = 2. 

   more » « less
3. Ultrasound Elasticity Imaging Using Physics-Based Models and Learning-Based Plug-and-Play Priors

   https://doi.org/10.1109/ICASSP39728.2021.9413652  

   Mohammadi, Narges; Doyley, Marvin M.; Cetin, Mujdat (June 2021, IEEE International Conference on Acoustics, Speech and Signal Processing)

   null (Ed.)
4. Learning continuous models for continuous physics

   https://doi.org/10.1038/s42005-023-01433-4  

   Krishnapriyan, Aditi S; Queiruga, Alejandro F; Erichson, N Benjamin; Mahoney, Michael W (December 2023, Communications Physics)

   Dynamical systems that evolve continuously over time are ubiquitous throughout science and engineering. Machine learning (ML) provides data-driven approaches to model and predict the dynamics of such systems. A core issue with this approach is that ML models are typically trained on discrete data, using ML methodologies that are not aware of underlying continuity properties. This results in models that often do not capture any underlying continuous dynamics—either of the system of interest, or indeed of any related system. To address this challenge, we develop a convergence test based on numerical analysis theory. Our test verifies whether a model has learned a function that accurately approximates an underlying continuous dynamics. Models that fail this test fail to capture relevant dynamics, rendering them of limited utility for many scientific prediction tasks; while models that pass this test enable both better interpolation and better extrapolation in multiple ways. Our results illustrate how principled numerical analysis methods can be coupled with existing ML training/testing methodologies to validate models for science and engineering applications. 

   more » « less
5. Hyperspectral dark field optical microscopy for orientational imaging of a single plasmonic nanocube using a physics-based learning method

   https://doi.org/10.1039/D2NA00469K  

   Mehta, Nishir; Mahigir, Amirreza; Veronis, Georgios; Gartia, Manas Ranjan (September 2022, Nanoscale Advances)

   Rotational dynamics at the molecular level could provide additional data regarding protein diffusion and cytoskeleton formation at the cellular level. Due to the isotropic emission pattern of fluorescence molecules, it is challenging to extract rotational information from them during imaging. Metal nanoparticles show a polarization-dependent response and could be used for sensing rotational motion. Nanoparticles as an orientation sensing probe offer bio-compatibility and robustness against photo-blinking and photo-bleaching compared to conventional fluorescent molecules. Previously, asymmetric geometrical structures such as nanorods have been used for orientational imaging. Here, we show orientational imaging of symmetric geometrical structures such as 100 nm isolated silver nanocubes by coupling a hyperspectral detector and a focused ion beam (FIB)-fabricated correlating substrate. More than 100 nanocubes are analyzed to confirm spectral shifts in the scattering spectra due to variations in the orientation of the nanocubes with respect to the incoming light. Results are further validated using finite-difference time-domain simulations. Our observations suggest a novel strategy for high-throughput orientation imaging of nanoparticles. 

   more » « less