Single-Shot Autofocusing of Microscopy Images Using Deep Learning
Source abstract
Abstract
Autofocusing is a critical step for high-quality microscopic imaging of specimens, especially for measurements that extend over time covering large fields of view. Autofocusing is generally practiced using two main approaches. Hardware-based optical autofocusing methods rely on additional distance sensors that are integrated with a microscopy system. Algorithmic autofocusing methods, on the other hand, regularly require axial scanning through the sample volume, leading to longer imaging times, which might also introduce phototoxicity and photobleaching on the sample. Here, we demonstrate a deep learning-based offline autofocusing method, termed Deep-R, that is trained to rapidly and blindly autofocus a single-shot microscopy image of a specimen that is acquired at an arbitrary out-of-focus plane. We illustrate the efficacy of Deep-R using various tissue sections that were imaged using fluorescence and brightfield microscopy modalities and demonstrate snapshot autofocusing under different scenarios, such as a uniform axial defocus as well as a sample tilt within the field-of-view. Our results reveal that Deep-R is significantly faster when compared with standard online algorithmic autofocusing methods. This deep learning-based blind autofocusing framework opens up new opportunities for rapid microscopic imaging of large sample areas, also reducing the photon dose on the sample.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Image Processing Techniques and Applications · Advanced Fluorescence Microscopy Techniques · Digital Holography and Microscopy
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Electrical and Computer Engineering Department, University of California, Los Angeles, California 90095, United States
Bioengineering Department, University of California, Los Angeles, California 90095, United States
California Nano Systems Institute (CNSI), University of California, Los Angeles, California 90095, United States
David Geffen School of Medicine, University of California Los Angeles, California 90095, United States
Funding
National Science Foundation
References (57)
Show source-provided references
1. 10.1196/annals.1342.02910.1196/annals.1342.029 ↗
2. 10.1016/S0076-6879(06)14032-X10.1016/S0076-6879(06)14032-X ↗
3. 10.1364/OE.26.00235910.1364/OE.26.002359 ↗
4. 10.1111/j.1365-2818.2006.01550.x10.1111/j.1365-2818.2006.01550.x ↗
5. 10.1109/ICSENS.2010.569015310.1109/ICSENS.2010.5690153 ↗
6. 10.1364/OL.42.00337910.1364/OL.42.003379 ↗
7. 10.4103/2153-3539.8628210.4103/2153-3539.86282 ↗
8. 10.1364/BOE.6.00321010.1364/BOE.6.003210 ↗
9. 10.1101/17055510.1101/170555 ↗
10. 10.1117/1.JBO.17.3.03600810.1117/1.JBO.17.3.036008 ↗
11. 10.1002/jemt.2011810.1002/jemt.20118 ↗
12. 10.1002/cyto.99012030210.1002/cyto.990120302 ↗
13. 10.1364/OE.16.00867010.1364/OE.16.008670 ↗
14. 10.1364/BOE.7.00476310.1364/BOE.7.004763 ↗
15. 10.1364/BOE.9.00160110.1364/BOE.9.001601 ↗
16. 10.1364/BOE.37978010.1364/BOE.379780 ↗
17. 10.1073/pnas.94.20.1063010.1073/pnas.94.20.10630 ↗
18. 10.1364/AO.58.00300310.1364/AO.58.003003 ↗
19. 10.1063/1.504696610.1063/1.5046966 ↗
20. 10.1117/1.JBO.22.8.08601210.1117/1.JBO.22.8.086012 ↗
21. 10.1038/s41592-019-0458-z10.1038/s41592-019-0458-z ↗
22. 10.1364/OPTICA.4.00143710.1364/OPTICA.4.001437 ↗
23. 10.1038/s41592-018-0239-010.1038/s41592-018-0239-0 ↗
24. 10.1038/s41551-019-0362-y10.1038/s41551-019-0362-y ↗
25. 10.1038/s41377-019-0129-y10.1038/s41377-019-0129-y ↗
26. 10.1364/OPTICA.5.00045810.1364/OPTICA.5.000458 ↗
27. 10.1038/nbt.410610.1038/nbt.4106 ↗
28. 10.1038/lsa.2017.14110.1038/lsa.2017.141 ↗
29. 10.1364/OPTICA.5.00070410.1364/OPTICA.5.000704 ↗
30. 10.1364/OPTICA.4.00111710.1364/OPTICA.4.001117 ↗
31. 10.1364/OPTICA.6.00079410.1364/OPTICA.6.000794 ↗
32. 10.1038/s41592-019-0622-510.1038/s41592-019-0622-5 ↗
33. 10.1364/JOSA.62.00005510.1364/JOSA.62.000055 ↗
34. 10.1086/11160510.1086/111605 ↗
35. 10.1002/jemt.2265010.1002/jemt.22650 ↗
36. 10.1109/TPAMI.2011.14810.1109/TPAMI.2011.148 ↗
37. 10.1109/ICIP.2018.845173610.1109/ICIP.2018.8451736 ↗
38. Goodfellow I. · 2014 · 2672
39. 10.1111/j.1365-2818.1988.tb04620.x10.1111/j.1365-2818.1988.tb04620.x ↗
40. 10.2307/237231310.2307/2372313 ↗
41. 10.1016/j.ymeth.2016.12.01510.1016/j.ymeth.2016.12.015 ↗
42. 10.1038/nmeth.208310.1038/nmeth.2083 ↗
43. 10.1177/108705711142029210.1177/1087057111420292 ↗
44. Autofocus manual - Micro-Manager https://micro-manager.org/wiki/Autofocus_manual (accessed Jan 14, 2020).
45. 10.14440/jbm.2014.3610.14440/jbm.2014.36 ↗
46. Brent R. P. · 2013
47. 10.1109/83.65084810.1109/83.650848 ↗
48. 10.1002/jemt.2009210.1002/jemt.20092 ↗
49. 10.1007/978-3-319-24574-4_2810.1007/978-3-319-24574-4_28 ↗
50. 10.1109/ACSSC.2003.129221610.1109/ACSSC.2003.1292216 ↗
51. 10.1090/conm/443/0855510.1090/conm/443/08555 ↗
52. 10.1109/3DV.2016.3210.1109/3DV.2016.32 ↗
53. 10.1007/s00261-019-01929-010.1007/s00261-019-01929-0 ↗
54. 10.1109/TCI.2016.264486510.1109/TCI.2016.2644865 ↗
55. Kingma D. P. · arXiv:1412.6980 [cs] · 2017 · na
56. Othman S. A. · Gen. Math. Notes · 2014 · 21 · 118
57. 10.1109/ICIP.2008.471180210.1109/ICIP.2008.4711802 ↗