PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The trade-off between throughput and image quality is an inherent challenge in microscopy. To improve throughput, compressive imaging under-samples image signals; the images are then computationally reconstructed. However, the information loss in the acquisition process sets the compression bounds. Here we propose differentiable compressive fluorescence microscopy (∂μ) that includes a realistic generalizable forward model with learnable-physical parameters (i.e. illumination patterns), and a novel physics-inspired inverse model. The cascaded model is end-to-end differentiable and can learn optimal compressive sampling schemes through training data. Proposed learned sampling outperforms widely used traditional compressive sampling schemes at higher compressions. We also demonstrate task-aware sampling (e.g. segmentation-aware) with the proposed framework.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Udith Haputhanthri, Andrew Seeber, Dushan N. Wadduwage, "Differentiable microscopy for content and task aware compressive fluorescence imaging (Conference Presentation)," Proc. SPIE PC12390, High-Speed Biomedical Imaging and Spectroscopy VIII, PC1239003 (16 March 2023); https://doi.org/10.1117/12.2651584