An Efficient Inference Frame for SMLM (Single-Molecule Localization Microscopy)
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909334179414016 |
|---|---|
| author | Luo, Tingdan |
| author_facet | Luo, Tingdan |
| contents | Single-molecule localization microscopy (SMLM) surpasses the diffraction limit, achieving subcellular resolution. Traditional SMLM analysis methods often rely on point spread function (PSF) model fitting, limiting the application of complex PSF models. In recent years, deep learning approaches have significantly improved SMLM algorithms, yielding promising results. However, limitations in inference speed and model size have restricted the widespread adoption of deep learning in practical applications. To address these challenges, this paper proposes an efficient model deployment framework and introduces a lightweight neural network, DilatedLoc, aimed at enhancing both image reconstruction quality and inference speed. Compared to leading network models, DilatedLoc reduces network parameters to under 100 MB and achieves a 50% improvement in inference speed, with superior GPU utilization through a novel deployment architecture compatible with various network models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02314 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Efficient Inference Frame for SMLM (Single-Molecule Localization Microscopy) Luo, Tingdan Quantitative Methods Computational Engineering, Finance, and Science Image and Video Processing Single-molecule localization microscopy (SMLM) surpasses the diffraction limit, achieving subcellular resolution. Traditional SMLM analysis methods often rely on point spread function (PSF) model fitting, limiting the application of complex PSF models. In recent years, deep learning approaches have significantly improved SMLM algorithms, yielding promising results. However, limitations in inference speed and model size have restricted the widespread adoption of deep learning in practical applications. To address these challenges, this paper proposes an efficient model deployment framework and introduces a lightweight neural network, DilatedLoc, aimed at enhancing both image reconstruction quality and inference speed. Compared to leading network models, DilatedLoc reduces network parameters to under 100 MB and achieves a 50% improvement in inference speed, with superior GPU utilization through a novel deployment architecture compatible with various network models. |
| title | An Efficient Inference Frame for SMLM (Single-Molecule Localization Microscopy) |
| topic | Quantitative Methods Computational Engineering, Finance, and Science Image and Video Processing |
| url | https://arxiv.org/abs/2410.02314 |