Scalable and lightweight deep learning for efficient high accuracy single-molecule localization microscopy

Abstract Deep learning has significantly improved the performance of single-molecule localization microscopy (SMLM), but many existing methods remain computationally intensive, limiting their applicability in high-throughput settings. To address these challenges, we present LiteLoc, a scalable analy...

Full description

Saved in:
Bibliographic Details
Main Authors: Yue Fei, Shuang Fu, Wei Shi, Ke Fang, Ruixiong Wang, Tianlun Zhang, Yiming Li
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-62662-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849234647073947648
author Yue Fei
Shuang Fu
Wei Shi
Ke Fang
Ruixiong Wang
Tianlun Zhang
Yiming Li
author_facet Yue Fei
Shuang Fu
Wei Shi
Ke Fang
Ruixiong Wang
Tianlun Zhang
Yiming Li
author_sort Yue Fei
collection DOAJ
description Abstract Deep learning has significantly improved the performance of single-molecule localization microscopy (SMLM), but many existing methods remain computationally intensive, limiting their applicability in high-throughput settings. To address these challenges, we present LiteLoc, a scalable analysis framework for high-throughput SMLM data analysis. LiteLoc employs a lightweight neural network architecture and integrates parallel processing across central processing unit (CPU) and graphics processing unit (GPU) resources to reduce latency and energy consumption without sacrificing localization accuracy. LiteLoc demonstrates substantial gains in processing speed and resource efficiency, making it an effective and scalable tool for routine SMLM workflows in biological research.
format Article
id doaj-art-b9684305da824744a2d126cbc2a465f2
institution Kabale University
issn 2041-1723
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-b9684305da824744a2d126cbc2a465f22025-08-20T04:03:06ZengNature PortfolioNature Communications2041-17232025-08-011611910.1038/s41467-025-62662-5Scalable and lightweight deep learning for efficient high accuracy single-molecule localization microscopyYue Fei0Shuang Fu1Wei Shi2Ke Fang3Ruixiong Wang4Tianlun Zhang5Yiming Li6Department of Biomedical Engineering, Southern University of Science and TechnologyDepartment of Biomedical Engineering, Southern University of Science and TechnologyDepartment of Biomedical Engineering, Southern University of Science and TechnologyDepartment of Biomedical Engineering, Southern University of Science and TechnologyDepartment of Biomedical Engineering, Southern University of Science and TechnologyDepartment of Biomedical Engineering, Southern University of Science and TechnologyDepartment of Biomedical Engineering, Southern University of Science and TechnologyAbstract Deep learning has significantly improved the performance of single-molecule localization microscopy (SMLM), but many existing methods remain computationally intensive, limiting their applicability in high-throughput settings. To address these challenges, we present LiteLoc, a scalable analysis framework for high-throughput SMLM data analysis. LiteLoc employs a lightweight neural network architecture and integrates parallel processing across central processing unit (CPU) and graphics processing unit (GPU) resources to reduce latency and energy consumption without sacrificing localization accuracy. LiteLoc demonstrates substantial gains in processing speed and resource efficiency, making it an effective and scalable tool for routine SMLM workflows in biological research.https://doi.org/10.1038/s41467-025-62662-5
spellingShingle Yue Fei
Shuang Fu
Wei Shi
Ke Fang
Ruixiong Wang
Tianlun Zhang
Yiming Li
Scalable and lightweight deep learning for efficient high accuracy single-molecule localization microscopy
Nature Communications
title Scalable and lightweight deep learning for efficient high accuracy single-molecule localization microscopy
title_full Scalable and lightweight deep learning for efficient high accuracy single-molecule localization microscopy
title_fullStr Scalable and lightweight deep learning for efficient high accuracy single-molecule localization microscopy
title_full_unstemmed Scalable and lightweight deep learning for efficient high accuracy single-molecule localization microscopy
title_short Scalable and lightweight deep learning for efficient high accuracy single-molecule localization microscopy
title_sort scalable and lightweight deep learning for efficient high accuracy single molecule localization microscopy
url https://doi.org/10.1038/s41467-025-62662-5
work_keys_str_mv AT yuefei scalableandlightweightdeeplearningforefficienthighaccuracysinglemoleculelocalizationmicroscopy
AT shuangfu scalableandlightweightdeeplearningforefficienthighaccuracysinglemoleculelocalizationmicroscopy
AT weishi scalableandlightweightdeeplearningforefficienthighaccuracysinglemoleculelocalizationmicroscopy
AT kefang scalableandlightweightdeeplearningforefficienthighaccuracysinglemoleculelocalizationmicroscopy
AT ruixiongwang scalableandlightweightdeeplearningforefficienthighaccuracysinglemoleculelocalizationmicroscopy
AT tianlunzhang scalableandlightweightdeeplearningforefficienthighaccuracysinglemoleculelocalizationmicroscopy
AT yimingli scalableandlightweightdeeplearningforefficienthighaccuracysinglemoleculelocalizationmicroscopy