Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash 92 tok/s
Gemini 2.5 Pro 50 tok/s Pro
GPT-5 Medium 42 tok/s
GPT-5 High 43 tok/s Pro
GPT-4o 103 tok/s
GPT OSS 120B 462 tok/s Pro
Kimi K2 202 tok/s Pro
2000 character limit reached

AI-driven projection tomography with multicore fibre-optic cell rotation (2312.07631v1)

Published 12 Dec 2023 in physics.med-ph, cs.AI, eess.IV, physics.bio-ph, and physics.optics

Abstract: Optical tomography has emerged as a non-invasive imaging method, providing three-dimensional insights into subcellular structures and thereby enabling a deeper understanding of cellular functions, interactions, and processes. Conventional optical tomography methods are constrained by a limited illumination scanning range, leading to anisotropic resolution and incomplete imaging of cellular structures. To overcome this problem, we employ a compact multi-core fibre-optic cell rotator system that facilitates precise optical manipulation of cells within a microfluidic chip, achieving full-angle projection tomography with isotropic resolution. Moreover, we demonstrate an AI-driven tomographic reconstruction workflow, which can be a paradigm shift from conventional computational methods, often demanding manual processing, to a fully autonomous process. The performance of the proposed cell rotation tomography approach is validated through the three-dimensional reconstruction of cell phantoms and HL60 human cancer cells. The versatility of this learning-based tomographic reconstruction workflow paves the way for its broad application across diverse tomographic imaging modalities, including but not limited to flow cytometry tomography and acoustic rotation tomography. Therefore, this AI-driven approach can propel advancements in cell biology, aiding in the inception of pioneering therapeutics, and augmenting early-stage cancer diagnostics.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (66)
  1. Kim, Y. et al. Common-path diffraction optical tomography for investigation of three-dimensional structures and dynamics of biological cells. \JournalTitleOptics express 22, 10398–10407 (2014).
  2. Tomographic phase microscopy: principles and applications in bioimaging. \JournalTitleJOSA B 34, B64–B77 (2017).
  3. Li, J. et al. High-speed in vitro intensity diffraction tomography. \JournalTitleAdvanced Photonics 1, 066004–066004 (2019).
  4. Li, J. et al. Transport of intensity diffraction tomography with non-interferometric synthetic aperture for three-dimensional label-free microscopy. \JournalTitleLight: Science & Applications 11, 1–14 (2022).
  5. Cotte, Y. et al. Marker-free phase nanoscopy. \JournalTitleNature Photonics 7, 113–117 (2013).
  6. 3d intensity and phase imaging from light field measurements in an led array microscope. \JournalTitleoptica 2, 104–111 (2015).
  7. Park, S. et al. Label-free tomographic imaging of lipid droplets in foam cells for machine-learning-assisted therapeutic evaluation of targeted nanodrugs. \JournalTitleACS nano 14, 1856–1865 (2020).
  8. Lim, J. et al. Comparative study of iterative reconstruction algorithms for missing cone problems in optical diffraction tomography. \JournalTitleOptics express 23, 16933–16948 (2015).
  9. High-fidelity optical diffraction tomography of multiple scattering samples. \JournalTitleLight: Science & Applications 8, 1–12 (2019).
  10. Exact interior reconstruction from truncated limited-angle projection data. \JournalTitleInternational Journal of Biomedical Imaging 2008 (2008).
  11. Globally convergent edge-preserving regularized reconstruction: an application to limited-angle tomography. \JournalTitleIEEE Transactions on Image Processing 7, 204–221 (1998).
  12. Kamilov, U. S. et al. Learning approach to optical tomography. \JournalTitleOptica 2, 517–522 (2015).
  13. Ryu, D. et al. Deepregularizer: rapid resolution enhancement of tomographic imaging using deep learning. \JournalTitleIEEE Transactions on Medical Imaging 40, 1508–1518 (2021).
  14. Dense u-net for limited angle tomography of sound pressure fields. \JournalTitleApplied Sciences 11, 4570 (2021).
  15. Fauver, M. et al. Three-dimensional imaging of single isolated cell nuclei using optical projection tomography. \JournalTitleOptics express 13, 4210–4223 (2005).
  16. Simon, B. et al. Tomographic diffractive microscopy with isotropic resolution. \JournalTitleOptica 4, 460, DOI: 10.1364/optica.4.000460 (2017).
  17. Merola, F. et al. Tomographic flow cytometry by digital holography. \JournalTitleLight: Science & Applications 6, e16241–e16241 (2017).
  18. Schürmann, M. et al. Three-dimensional correlative single-cell imaging utilizing fluorescence and refractive index tomography. \JournalTitleJournal of biophotonics 11, e201700145 (2018).
  19. Villone, M. M. et al. Full-angle tomographic phase microscopy of flowing quasi-spherical cells. \JournalTitleLab on a Chip 18, 126–131 (2018).
  20. Pirone, D. et al. Stain-free identification of cell nuclei using tomographic phase microscopy in flow cytometry. \JournalTitleNature Photonics 1–9 (2022).
  21. Habaza, M. et al. Rapid 3d refractive-index imaging of live cells in suspension without labeling using dielectrophoretic cell rotation. \JournalTitleAdvanced Science 4, 1600205 (2017).
  22. Soffe, R. et al. Controlled rotation and vibration of patterned cell clusters using dielectrophoresis. \JournalTitleAnalytical chemistry 87, 2389–2395 (2015).
  23. Ahmed, D. et al. Rotational manipulation of single cells and organisms using acoustic waves. \JournalTitleNature communications 7, 1–11 (2016).
  24. Zhang, S. P. et al. Digital acoustofluidics enables contactless and programmable liquid handling. \JournalTitleNature communications 9, 1–11 (2018).
  25. Controlled orientation and sustained rotation of biological samples in a sono-optical microfluidic device. \JournalTitleLab on a Chip 21, 1563–1578 (2021).
  26. Tomographic active optical trapping of arbitrarily shaped objects by exploiting 3D refractive index maps. \JournalTitleNature Communications 8, DOI: 10.1038/ncomms15340 (2017).
  27. Isotropically resolved label-free tomographic imaging based on tomographic moulds for optical trapping. \JournalTitleLight: Science & Applications 10, 1–9 (2021).
  28. Kreysing, M. et al. Dynamic operation of optical fibres beyond the single-mode regime facilitates the orientation of biological cells. \JournalTitleNature communications 5, 5481 (2014).
  29. Leite, I. T. et al. Three-dimensional holographic optical manipulation through a high-numerical-aperture soft-glass multimode fibre. \JournalTitleNature Photonics 12, 33–39 (2018).
  30. Rapid computational cell-rotation around arbitrary axes in 3d with multi-core fiber. \JournalTitleBiomedical Optics Express 12, 3423–3437 (2021).
  31. Zuo, C. et al. Deep learning in optical metrology: a review. \JournalTitleLight: Science & Applications 11, 39 (2022).
  32. Feng, S. et al. Fringe pattern analysis using deep learning. \JournalTitleAdvanced Photonics 1, 025001–025001 (2019).
  33. Pirone, D. et al. Speeding up reconstruction of 3d tomograms in holographic flow cytometry via deep learning. \JournalTitleLab on a Chip 22, 793–804 (2022).
  34. Three-dimensional tomography of red blood cells using deep learning. \JournalTitleAdvanced Photonics 2, 026001–026001 (2020).
  35. Rivenson, Y. et al. Deep learning microscopy. \JournalTitleOptica 4, 1437–1443 (2017).
  36. Wang, H. et al. Deep learning enables cross-modality super-resolution in fluorescence microscopy. \JournalTitleNature methods 16, 103–110 (2019).
  37. Wu, J. et al. Learned end-to-end high-resolution lensless fiber imaging towards real-time cancer diagnosis. \JournalTitleScientific Reports 12, 18846 (2022).
  38. Greenwald, N. F. et al. Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning. \JournalTitleNature biotechnology 40, 555–565 (2022).
  39. Nygate, Y. N. et al. Holographic virtual staining of individual biological cells. \JournalTitleProceedings of the National Academy of Sciences 117, 9223–9231 (2020).
  40. Bai, B. et al. Deep learning-enabled virtual histological staining of biological samples. \JournalTitleLight: Science & Applications 12, 57 (2023).
  41. Sun, J. et al. Real-time complex light field generation through a multi-core fiber with deep learning. \JournalTitleScientific reports 12, 1–10 (2022).
  42. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, 779–788 (2016).
  43. Transfer learning for pedestrian detection. \JournalTitleNeurocomputing 100, 51–57 (2013).
  44. Spannbauer, A. Python video stabilization. https://github.com/AdamSpannbauer/python_video_stab (2021).
  45. Effects of ct image segmentation methods on the accuracy of long bone 3d reconstructions. \JournalTitleMedical engineering & physics 33, 226–233 (2011).
  46. Arganda-Carreras, I. et al. Trainable weka segmentation: a machine learning tool for microscopy pixel classification. \JournalTitleBioinformatics 33, 2424–2426 (2017).
  47. A deep learning-based algorithm for 2-d cell segmentation in microscopy images. \JournalTitleBMC bioinformatics 19, 1–11 (2018).
  48. Gräbel, P. et al. State of the art cell detection in bone marrow whole slide images. \JournalTitleJournal of Pathology Informatics 12, 36 (2021).
  49. Iwana, D. et al. Accuracy of angle and position of the cup using computed tomography-based navigation systems in total hip arthroplasty. \JournalTitleComputer Aided Surgery 18, 187–194 (2013).
  50. An analysis and implementation of the harris corner detector. \JournalTitleImage Processing On Line (2018).
  51. Optical flow constraints on deformable models with applications to face tracking. \JournalTitleInternational Journal of Computer Vision 38, 99–127 (2000).
  52. Gao, Z. et al. Distortion correction for particle image velocimetry using multiple-input deep convolutional neural network and hartmann-shack sensing. \JournalTitleOptics Express 29, 18669–18687 (2021).
  53. Heckel, S. et al. Beyond janus geometry: characterization of flow fields around nonspherical photocatalytic microswimmers. \JournalTitleAdvanced Science 9, 2105009 (2022).
  54. Koskela, O. et al. Gaussian light model in brightfield optical projection tomography. \JournalTitleScientific reports 9, 13934 (2019).
  55. The coefficient of determination r-squared is more informative than smape, mae, mape, mse and rmse in regression analysis evaluation. \JournalTitlePeerJ Computer Science 7, e623 (2021).
  56. Multiscale structural similarity for image quality assessment. In The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, vol. 2, 1398–1402 (Ieee, 2003).
  57. Is there a relationship between peak-signal-to-noise ratio and structural similarity index measure? \JournalTitleIET Image Processing 7, 12–24 (2013).
  58. Charrière, F. et al. Cell refractive index tomography by digital holographic microscopy. \JournalTitleOptics letters 31, 178–180 (2006).
  59. Yoon, J. et al. Identification of non-activated lymphocytes using three-dimensional refractive index tomography and machine learning. \JournalTitleScientific reports 7, 1–10 (2017).
  60. X-ray tomography of whole cells. \JournalTitleCurrent opinion in structural biology 15, 593–600 (2005).
  61. Ultra-thin 3d lensless fiber endoscopy using diffractive optical elements and deep neural networks. \JournalTitleLight: Advanced Manufacturing 2, 1–10 (2021).
  62. Minimal-invasive faseroptische endomikroskopie für die medizin. \JournalTitletm-Technisches Messen 89, 25–30 (2022).
  63. Barthel, K. U. 3d-data representation with imagej. In ImageJ Conference (Citeseer, 2006).
  64. Protective effect of methylcellulose and other polymers on insect cells subjected to laminar shear stress. In Biotechnology progress, 6, 5, 383–390 (ACS Publications, 1990).
  65. Source data for AI-driven projection tomography with multicore fibre-optic cell rotation. FigShare, https://doi.org/10.6084/m9.figshare.24523618 (2023).
  66. AI-driven autonomous tomographic reconstruction workflow. Zenodo, https://doi.org/10.5281/zenodo.10124421 (2023).
Citations (17)
View on Semantic Scholar
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Dice Question Streamline Icon: https://streamlinehq.com

Follow-up Questions

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now