Yiming Li

Neural-physics adaptive reconstruction reveals 3D subcellular nanostructures over a large depth of field Achieving large depth-of-field super-resolution imaging deep inside samples is often hindered by unknown aberrations and overlapping molecular signals in 3D single-molecule localization microscopy. He...

LiteLoc is still a PSF supervised learning method. It does not estimate PSF from the data. We also developed LUNAR, a self-supervised learning method, that can learn PSF from the data. www.biorxiv.org/content/10.1...

The speed evaluation includes data reading, data analysis and data saving.

Scalable and lightweight deep learning for efficient high accuracy single-molecule localization microscopy Nature Communications - This study presents LiteLoc, a lightweight and scalable AI model for efficient and accurate single molecule localization microscopy data analysis, bringing real-time...

We’re excited to share LiteLoc — a lightweight and scalable deep learning framework for high-throughput single-molecule localization microscopy, enabling analysis speed of >500 MB/s on 8× RTX 4090 GPUs without compromising accuracy. rdcu.be/eztp6

Neural-physics adaptive reconstruction reveals 3D subcellular nanostructures over a large depth of field Achieving large depth-of-field super-resolution imaging deep inside samples is often hindered by unknown aberrations and overlapping molecular signals in 3D single-molecule localization microscopy. Here, we present LUNAR, a blind localization method that simultaneously resolves overlapping molecular signals and corrects for aberrations using a neural-physics model. Through self-supervised learning on single-molecule data without requiring prior knowledge or accurate calibration, LUNAR synergistically optimizes a physical model with a neural network to estimate key physical parameters (e.g., 3D positions, photons, aberrations) of molecules. Its hybrid Transformer network effectively handles PSFs of varying sizes, achieving theoretically maximum localization precision of consecutive blinking events. Extensive simulations and experiments demonstrate that LUNAR consistently outperforms current state-of-the-art methods, reducing localization error by up to sixfold in the presence of unknown aberrations and molecular overlaps, enabling high-fidelity whole-cell reconstruction of mitochondria, nucleus, and neuronal cytoskeleton at great depths. ### Competing Interest Statement The authors have declared no competing interest.

Nice preprint on SMLM localizations with NN,
LUNAR.
The network learns both locations and PSFs
www.biorxiv.org/content/10.1...