1
|
Moser LM, Gogoberidze N, Papaleo A, Lucas A, Dao D, Friedrich CA, Paavolainen L, Molnar C, Stirling DR, Hung J, Wang R, Tromans-Coia C, Li B, Evans EL, Eliceiri KW, Horvath P, Carpenter AE, Cimini BA. Piximi - An Images to Discovery web tool for bioimages and beyond. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.06.03.597232. [PMID: 38895349 PMCID: PMC11185650 DOI: 10.1101/2024.06.03.597232] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/21/2024]
Abstract
Deep learning has greatly accelerated research in biological image analysis yet it often requires programming skills and specialized tool installation. Here we present Piximi, a modern, no-programming image analysis tool leveraging deep learning. Implemented as a web application at Piximi.app, Piximi requires no installation and can be accessed by any modern web browser. Its client-only architecture preserves the security of researcher data by running all computation locally. Piximi offers four core modules: a deep learning classifier, an image annotator, measurement modules, and pre-trained deep learning segmentation modules. Piximi is interoperable with existing tools and workflows by supporting import and export of common data and model formats. The intuitive researcher interface and easy access to Piximi allows biological researchers to obtain insights into images within just a few minutes. Piximi aims to bring deep learning-powered image analysis to a broader community by eliminating barriers to entry.
Collapse
Affiliation(s)
- Levin M Moser
- Imaging Platform, Broad Institute of MIT and Harvard, Cambridge MA, USA
| | - Nodar Gogoberidze
- Imaging Platform, Broad Institute of MIT and Harvard, Cambridge MA, USA
| | - Andréa Papaleo
- Imaging Platform, Broad Institute of MIT and Harvard, Cambridge MA, USA
| | - Alice Lucas
- Imaging Platform, Broad Institute of MIT and Harvard, Cambridge MA, USA
| | | | | | - Lassi Paavolainen
- Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki, Finland
| | - Csaba Molnar
- Imaging Platform, Broad Institute of MIT and Harvard, Cambridge MA, USA
- Synthetic and Systems Biology Unit, HUN-REN Biological Research Centre (BRC), Szeged, Hungary
| | - David R Stirling
- Imaging Platform, Broad Institute of MIT and Harvard, Cambridge MA, USA
| | - Jane Hung
- Department of Chemical Engineering, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA
| | - Rex Wang
- Data Sciences Platform, Broad Institute of MIT and Harvard, Cambridge MA, USA
| | | | - Bin Li
- Center for Quantitative Cell Imaging, University of Wisconsin-Madison, Madison, WI, USA
| | - Edward L Evans
- Center for Quantitative Cell Imaging, University of Wisconsin-Madison, Madison, WI, USA
| | - Kevin W Eliceiri
- Center for Quantitative Cell Imaging, University of Wisconsin-Madison, Madison, WI, USA
| | - Peter Horvath
- Synthetic and Systems Biology Unit, HUN-REN Biological Research Centre (BRC), Szeged, Hungary
- Synthetic and Systems Biology Unit, HUN-REN Biological Research Centre (BRC), Szeged, Hungary; Institute of AI for Health, Helmholtz Zentrum München, Neuherberg, Germany
| | - Anne E Carpenter
- Imaging Platform, Broad Institute of MIT and Harvard, Cambridge MA, USA
| | - Beth A Cimini
- Imaging Platform, Broad Institute of MIT and Harvard, Cambridge MA, USA
| |
Collapse
|
2
|
Gogoberidze N, Cimini BA. Defining the boundaries: challenges and advances in identifying cells in microscopy images. Curr Opin Biotechnol 2024; 85:103055. [PMID: 38142646 PMCID: PMC11170924 DOI: 10.1016/j.copbio.2023.103055] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2023] [Revised: 11/28/2023] [Accepted: 11/28/2023] [Indexed: 12/26/2023]
Abstract
Segmentation, or the outlining of objects within images, is a critical step in the measurement and analysis of cells within microscopy images. While improvements continue to be made in tools that rely on classical methods for segmentation, deep learning-based tools increasingly dominate advances in the technology. Specialist models such as Cellpose continue to improve in accuracy and user-friendliness, and segmentation challenges such as the Multi-Modality Cell Segmentation Challenge continue to push innovation in accuracy across widely varying test data as well as efficiency and usability. Increased attention on documentation, sharing, and evaluation standards is leading to increased user-friendliness and acceleration toward the goal of a truly universal method.
Collapse
Affiliation(s)
| | - Beth A Cimini
- Imaging Platform, Broad Institute, Cambridge, MA 02142, USA.
| |
Collapse
|
3
|
Phillips TA, Marcotti S, Cox S, Parsons M. Imaging actin organisation and dynamics in 3D. J Cell Sci 2024; 137:jcs261389. [PMID: 38236161 PMCID: PMC10906668 DOI: 10.1242/jcs.261389] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/19/2024] Open
Abstract
The actin cytoskeleton plays a critical role in cell architecture and the control of fundamental processes including cell division, migration and survival. The dynamics and organisation of F-actin have been widely studied in a breadth of cell types on classical two-dimensional (2D) surfaces. Recent advances in optical microscopy have enabled interrogation of these cytoskeletal networks in cells within three-dimensional (3D) scaffolds, tissues and in vivo. Emerging studies indicate that the dimensionality experienced by cells has a profound impact on the structure and function of the cytoskeleton, with cells in 3D environments exhibiting cytoskeletal arrangements that differ to cells in 2D environments. However, the addition of a third (and fourth, with time) dimension leads to challenges in sample preparation, imaging and analysis, necessitating additional considerations to achieve the required signal-to-noise ratio and spatial and temporal resolution. Here, we summarise the current tools for imaging actin in a 3D context and highlight examples of the importance of this in understanding cytoskeletal biology and the challenges and opportunities in this domain.
Collapse
Affiliation(s)
- Thomas A. Phillips
- Randall Centre for Cell and Molecular Biophysics, King's College London, New Hunts House, Guys Campus, London SE1 1UL, UK
| | - Stefania Marcotti
- Randall Centre for Cell and Molecular Biophysics, King's College London, New Hunts House, Guys Campus, London SE1 1UL, UK
- Microscopy Innovation Centre, King's College London, Guys Campus, London SE1 1UL, UK
| | - Susan Cox
- Randall Centre for Cell and Molecular Biophysics, King's College London, New Hunts House, Guys Campus, London SE1 1UL, UK
| | - Maddy Parsons
- Randall Centre for Cell and Molecular Biophysics, King's College London, New Hunts House, Guys Campus, London SE1 1UL, UK
| |
Collapse
|