U-Net-based deep learning for tracking and quantitative analysis of intracellular vesicles in time-lapse microscopy images
Fluorescence microscopy has become an essential tool for biologists, to visualize the dynamics of intracellular structures with specific labeling. Quantitatively measuring the dynamics of moving objects inside the cell is pivotal for understanding of the underlying regulatory mechanism. Protein-cont...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
World Scientific Publishing
2022-09-01
|
| Series: | Journal of Innovative Optical Health Sciences |
| Subjects: | |
| Online Access: | https://www.worldscientific.com/doi/10.1142/S1793545822500316 |
| _version_ | 1798019570853740544 |
|---|---|
| author | Zhichao Liu Heng Zhang Luhong Jin Jincheng Chen Alexander Nedzved Sergey Ablameyko Qing Ma Jiahui Yu Yingke Xu |
| author_facet | Zhichao Liu Heng Zhang Luhong Jin Jincheng Chen Alexander Nedzved Sergey Ablameyko Qing Ma Jiahui Yu Yingke Xu |
| author_sort | Zhichao Liu |
| collection | DOAJ |
| description | Fluorescence microscopy has become an essential tool for biologists, to visualize the dynamics of intracellular structures with specific labeling. Quantitatively measuring the dynamics of moving objects inside the cell is pivotal for understanding of the underlying regulatory mechanism. Protein-containing vesicles are involved in various biological processes such as material transportation, organelle interaction, and hormonal regulation, whose dynamic characteristics are significant to disease diagnosis and drug screening. Although some algorithms have been developed for vesicle tracking, most of them have limited performance when dealing with images with low resolution, poor signal-to-noise ratio (SNR) and complicated motion. Here, we proposed a novel deep learning-based method for intracellular vesicle tracking. We trained the U-Net for vesicle localization and motion classification, with demonstrates great performance in both simulated datasets and real biological samples. By combination with fan-shaped tracker (FsT) we have previously developed, this hybrid new algorithm significantly improved the performance of particle tracking with the function of subsequently automated vesicle motion classification. Furthermore, its performance was further demonstrated in analyzing with vesicle dynamics in different temperature, which achieved reasonable outcomes. Thus, we anticipate that this novel method would have vast applications in analyzing the vesicle dynamics in living cells. |
| first_indexed | 2024-04-11T16:42:43Z |
| format | Article |
| id | doaj.art-985958ed105945e6bd13b6468a633972 |
| institution | Directory Open Access Journal |
| issn | 1793-5458 1793-7205 |
| language | English |
| last_indexed | 2024-04-11T16:42:43Z |
| publishDate | 2022-09-01 |
| publisher | World Scientific Publishing |
| record_format | Article |
| series | Journal of Innovative Optical Health Sciences |
| spelling | doaj.art-985958ed105945e6bd13b6468a6339722022-12-22T04:13:38ZengWorld Scientific PublishingJournal of Innovative Optical Health Sciences1793-54581793-72052022-09-01150510.1142/S1793545822500316U-Net-based deep learning for tracking and quantitative analysis of intracellular vesicles in time-lapse microscopy imagesZhichao Liu0Heng Zhang1Luhong Jin2Jincheng Chen3Alexander Nedzved4Sergey Ablameyko5Qing Ma6Jiahui Yu7Yingke Xu8Department of Biomedical Engineering, MOE Key Laboratory of Biomedical Engineering, State Key Laboratory of Modern Optical Instrumentation, Zhejiang Provincial Key Laboratory of Cardio-Cerebral Vascular Detection Technology and Medicinal Effectiveness Appraisal, Zhejiang University, Hangzhou 310027, P. R. ChinaDepartment of Biomedical Engineering, MOE Key Laboratory of Biomedical Engineering, State Key Laboratory of Modern Optical Instrumentation, Zhejiang Provincial Key Laboratory of Cardio-Cerebral Vascular Detection Technology and Medicinal Effectiveness Appraisal, Zhejiang University, Hangzhou 310027, P. R. ChinaDepartment of Biomedical Engineering, MOE Key Laboratory of Biomedical Engineering, State Key Laboratory of Modern Optical Instrumentation, Zhejiang Provincial Key Laboratory of Cardio-Cerebral Vascular Detection Technology and Medicinal Effectiveness Appraisal, Zhejiang University, Hangzhou 310027, P. R. ChinaDepartment of Biomedical Engineering, MOE Key Laboratory of Biomedical Engineering, State Key Laboratory of Modern Optical Instrumentation, Zhejiang Provincial Key Laboratory of Cardio-Cerebral Vascular Detection Technology and Medicinal Effectiveness Appraisal, Zhejiang University, Hangzhou 310027, P. R. ChinaNational Academy of Sciences, United Institute of Informatics Problems, Belarusian State University, Minsk 220012, Republic of BelarusNational Academy of Sciences, United Institute of Informatics Problems, Belarusian State University, Minsk 220012, Republic of BelarusHangzhou Dowell Photonics Measurement Company Limited, Hangzhou 310000, P. R. ChinaBinjiang Institute of Zhejiang University, Hangzhou 310053, P. R. ChinaDepartment of Biomedical Engineering, MOE Key Laboratory of Biomedical Engineering, State Key Laboratory of Modern Optical Instrumentation, Zhejiang Provincial Key Laboratory of Cardio-Cerebral Vascular Detection Technology and Medicinal Effectiveness Appraisal, Zhejiang University, Hangzhou 310027, P. R. ChinaFluorescence microscopy has become an essential tool for biologists, to visualize the dynamics of intracellular structures with specific labeling. Quantitatively measuring the dynamics of moving objects inside the cell is pivotal for understanding of the underlying regulatory mechanism. Protein-containing vesicles are involved in various biological processes such as material transportation, organelle interaction, and hormonal regulation, whose dynamic characteristics are significant to disease diagnosis and drug screening. Although some algorithms have been developed for vesicle tracking, most of them have limited performance when dealing with images with low resolution, poor signal-to-noise ratio (SNR) and complicated motion. Here, we proposed a novel deep learning-based method for intracellular vesicle tracking. We trained the U-Net for vesicle localization and motion classification, with demonstrates great performance in both simulated datasets and real biological samples. By combination with fan-shaped tracker (FsT) we have previously developed, this hybrid new algorithm significantly improved the performance of particle tracking with the function of subsequently automated vesicle motion classification. Furthermore, its performance was further demonstrated in analyzing with vesicle dynamics in different temperature, which achieved reasonable outcomes. Thus, we anticipate that this novel method would have vast applications in analyzing the vesicle dynamics in living cells.https://www.worldscientific.com/doi/10.1142/S1793545822500316Deep learningimage processingvesicle trackingfluorescence microscopyU-Net |
| spellingShingle | Zhichao Liu Heng Zhang Luhong Jin Jincheng Chen Alexander Nedzved Sergey Ablameyko Qing Ma Jiahui Yu Yingke Xu U-Net-based deep learning for tracking and quantitative analysis of intracellular vesicles in time-lapse microscopy images Journal of Innovative Optical Health Sciences Deep learning image processing vesicle tracking fluorescence microscopy U-Net |
| title | U-Net-based deep learning for tracking and quantitative analysis of intracellular vesicles in time-lapse microscopy images |
| title_full | U-Net-based deep learning for tracking and quantitative analysis of intracellular vesicles in time-lapse microscopy images |
| title_fullStr | U-Net-based deep learning for tracking and quantitative analysis of intracellular vesicles in time-lapse microscopy images |
| title_full_unstemmed | U-Net-based deep learning for tracking and quantitative analysis of intracellular vesicles in time-lapse microscopy images |
| title_short | U-Net-based deep learning for tracking and quantitative analysis of intracellular vesicles in time-lapse microscopy images |
| title_sort | u net based deep learning for tracking and quantitative analysis of intracellular vesicles in time lapse microscopy images |
| topic | Deep learning image processing vesicle tracking fluorescence microscopy U-Net |
| url | https://www.worldscientific.com/doi/10.1142/S1793545822500316 |
| work_keys_str_mv | AT zhichaoliu unetbaseddeeplearningfortrackingandquantitativeanalysisofintracellularvesiclesintimelapsemicroscopyimages AT hengzhang unetbaseddeeplearningfortrackingandquantitativeanalysisofintracellularvesiclesintimelapsemicroscopyimages AT luhongjin unetbaseddeeplearningfortrackingandquantitativeanalysisofintracellularvesiclesintimelapsemicroscopyimages AT jinchengchen unetbaseddeeplearningfortrackingandquantitativeanalysisofintracellularvesiclesintimelapsemicroscopyimages AT alexandernedzved unetbaseddeeplearningfortrackingandquantitativeanalysisofintracellularvesiclesintimelapsemicroscopyimages AT sergeyablameyko unetbaseddeeplearningfortrackingandquantitativeanalysisofintracellularvesiclesintimelapsemicroscopyimages AT qingma unetbaseddeeplearningfortrackingandquantitativeanalysisofintracellularvesiclesintimelapsemicroscopyimages AT jiahuiyu unetbaseddeeplearningfortrackingandquantitativeanalysisofintracellularvesiclesintimelapsemicroscopyimages AT yingkexu unetbaseddeeplearningfortrackingandquantitativeanalysisofintracellularvesiclesintimelapsemicroscopyimages |