Democratising deep learning for microscopy with ZeroCostDL4Mic

Nature Communications, Год журнала: 2021, Номер 12(1)

Опубликована: Апрель 15, 2021

Abstract Deep Learning (DL) methods are powerful analytical tools for microscopy and can outperform conventional image processing pipelines. Despite the enthusiasm innovations fuelled by DL technology, need to access compatible resources train networks leads an accessibility barrier that novice users often find difficult overcome. Here, we present ZeroCostDL4Mic, entry-level platform simplifying leveraging free, cloud-based computational of Google Colab. ZeroCostDL4Mic allows researchers with no coding expertise apply key perform tasks including segmentation (using U-Net StarDist), object detection YOLOv2), denoising CARE Noise2Void), super-resolution Deep-STORM), image-to-image translation Label-free prediction - fnet, pix2pix CycleGAN). Importantly, provide suitable quantitative each network evaluate model performance, allowing optimisation. We demonstrate application study multiple biological processes.

Язык: Английский

---

Focal adhesion dynamics in cellular function and disease

Cellular Signalling, Год журнала: 2021, Номер 85, С. 110046 - 110046

Опубликована: Май 15, 2021

Язык: Английский

---

iU-ExM: nanoscopy of organelles and tissues with iterative ultrastructure expansion microscopy

Nature Communications, Год журнала: 2023, Номер 14(1)

Опубликована: Ноя. 30, 2023

Expansion microscopy (ExM) is a highly effective technique for super-resolution fluorescence that enables imaging of biological samples beyond the diffraction limit with conventional microscopes. Despite development several enhanced protocols, ExM has not yet demonstrated ability to achieve precision nanoscopy techniques such as Single Molecule Localization Microscopy (SMLM). Here, address this limitation, we have developed an iterative ultrastructure expansion (iU-ExM) approach achieves SMLM-level resolution. With iU-ExM, it now possible visualize molecular architecture gold-standard samples, eight-fold symmetry nuclear pores or organization conoid in Apicomplexa. its wide-ranging applications, from isolated organelles cells and tissue, iU-ExM opens new avenues scientists studying structures functions.

Язык: Английский

---

Bright and stable monomeric green fluorescent protein derived from StayGold

Nature Methods, Год журнала: 2024, Номер 21(4), С. 657 - 665

Опубликована: Фев. 26, 2024

Язык: Английский

---

Quantification of tumor heterogeneity: from data acquisition to metric generation

Trends in biotechnology, Год журнала: 2021, Номер 40(6), С. 647 - 676

Опубликована: Дек. 28, 2021

Tumors are unique and complex ecosystems, in which heterogeneous cell subpopulations with variable molecular profiles, aggressiveness, proliferation potential coexist interact. Understanding how heterogeneity influences tumor progression has important clinical implications for improving diagnosis, prognosis, treatment response prediction. Several recent innovations data acquisition methods computational metrics have enabled the quantification of spatiotemporal across different scales organization. Here, we summarize most promising efforts from a common experimental perspective, discussing their advantages, shortcomings, challenges. With personalized medicine entering new era unprecedented opportunities, our vision is that future workflows integrating modalities, scales, dimensions to capture intricate aspects ecosystem open avenues improved patient care.

Язык: Английский

---

Unravelling cell migration: defining movement from the cell surface

Cell Adhesion & Migration, Год журнала: 2022, Номер 16(1), С. 25 - 64

Опубликована: Май 1, 2022

Cell motility is essential for life and development. Unfortunately, cell migration also linked to several pathological processes, such as cancer metastasis. Cells' ability migrate relies on many actors. Cells change their migratory strategy based phenotype the properties of surrounding microenvironment. is, therefore, an extremely complex phenomenon. Researchers have investigated more than a century. Recent discoveries uncovered some mysteries associated with mechanisms involved in migration, intracellular signaling mechanics. These findings involve different players, including transmembrane receptors, adhesive complexes, cytoskeletal components , nucleus, extracellular matrix. This review aims give global overview our current understanding migration.

Язык: Английский

---

Extending resolution within a single imaging frame

Nature Communications, Год журнала: 2022, Номер 13(1)

Опубликована: Дек. 2, 2022

Abstract The resolution of fluorescence microscopy images is limited by the physical properties light. In last decade, numerous super-resolution (SRM) approaches have been proposed to deal with such hindrance. Here we present Mean-Shift Super Resolution (MSSR), a new SRM algorithm based on Mean Shift theory, which extends spatial single beyond diffraction limit MSSR works low and high fluorophore densities, not architecture optical setup applicable as well temporal series. theoretical resolution, optimized real-world imaging conditions analysis image stacks, has measured be 40 nm. Furthermore, denoising capabilities that outperform other approaches. Along its wide accessibility, powerful, flexible, generic tool for multidimensional live cell applications.

Язык: Английский

---

High-fidelity 3D live-cell nanoscopy through data-driven enhanced super-resolution radial fluctuation

Nature Methods, Год журнала: 2023, Номер 20(12), С. 1949 - 1956

Опубликована: Ноя. 13, 2023

Abstract Live-cell super-resolution microscopy enables the imaging of biological structure dynamics below diffraction limit. Here we present enhanced radial fluctuations (eSRRF), substantially improving image fidelity and resolution compared to original SRRF method. eSRRF incorporates automated parameter optimization based on data itself, giving insight into trade-off between fidelity. We demonstrate across a range modalities systems. Notably, extend three dimensions by combining it with multifocus microscopy. This realizes live-cell volumetric an acquisition speed ~1 volume per second. provides accessible approach, maximizing information extraction varied experimental conditions while minimizing artifacts. Its optimal prediction strategy is generalizable, moving toward unbiased optimized analyses in

Язык: Английский

---

Imagining the future of optical microscopy: everything, everywhere, all at once

Communications Biology, Год журнала: 2023, Номер 6(1)

Опубликована: Окт. 28, 2023

The optical microscope has revolutionized biology since at least the 17

Язык: Английский

---

Live-cell imaging in the deep learning era

Current Opinion in Cell Biology, Год журнала: 2023, Номер 85, С. 102271 - 102271

Опубликована: Окт. 27, 2023

Live imaging is a powerful tool, enabling scientists to observe living organisms in real time. In particular, when combined with fluorescence microscopy, live allows the monitoring of cellular components high sensitivity and specificity. Yet, due critical challenges (i.e., drift, phototoxicity, dataset size), implementing analyzing resulting datasets rarely straightforward. Over past years, development bioimage analysis tools, including deep learning, changing how we perform imaging. Here briefly cover important computational methods aiding carrying out key tasks such as drift correction, denoising, super-resolution imaging, artificial labeling, tracking, time series analysis. We also recent advances self-driving microscopy.

Язык: Английский

---