Enhancing Deep Learning Based Structured Illumination Microscopy Reconstruction with Light Field Awareness
This work addresses the limitation of SIM for complex biological systems by improving reconstruction accuracy and robustness, though it is incremental as it builds on existing deep learning methods.
The paper tackled the problem of deep learning-based structured illumination microscopy (SIM) reconstruction struggling with out-of-distribution data by proposing an Awareness-of-Light-field SIM (AL-SIM) approach that directly estimates the actual light field, resulting in a 7% reduction in normalized root mean square error (NRMSE) and lower reconstruction artefacts.
Structured illumination microscopy (SIM) is a pivotal technique for dynamic subcellular imaging in live cells. Conventional SIM reconstruction algorithms depend on accurately estimating the illumination pattern and can introduce artefacts when this estimation is imprecise. Although recent deep learning-based SIM reconstruction methods have improved speed, accuracy, and robustness, they often struggle with out-of-distribution data. To address this limitation, we propose an Awareness-of-Light-field SIM (AL-SIM) reconstruction approach that directly estimates the actual light field to correct for errors arising from data distribution shifts. Through comprehensive experiments on both simulated filament structures and live BSC1 cells, our method demonstrates a 7% reduction in the normalized root mean square error (NRMSE) and substantially lowers reconstruction artefacts. By minimizing these artefacts and improving overall accuracy, AL-SIM broadens the applicability of SIM for complex biological systems.