MoBIE: a Fiji plugin for sharing and exploration of multi-modal cloud-hosted big image data

Pape, Constantin; Meechan, Kimberly; Moreva, Ekaterina; Schorb, Martin; Chiaruttini, Nicolas; Zinchenko, Valentyna; Vergara, Hernando; Mizzon, Giulia; Moore, Josh; Arendt, Detlev; Kreshuk, Anna; Schwab, Yannick

doi:10.1038/s41592-023-01776-4

Cited by 11 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CebraEM's strengths articulate around three pillars, with the aim to make it accessible to a wide community of users: (I) it avoids the necessity to intensively train a neural network, (II) the inference model is trained on annotations of the same target dataset that the user chooses to segment, thus approaching the result to the specific domain of the data, and (III) it yields a fully learned semantic instance segmentation. From a user perspective, the CebraEM workflow starts with the initialization of a CebraEM project which can be visualized using the MoBIE viewer (39). Using the viewer, the user navigates the dataset and selects suitable positions for ground truth cubes that contain the required target organelle(s) (Fig.…”

Section: Resultsmentioning

confidence: 99%

“…1c). At any time, from initialization to the final segmentations, the CebraEM project with its associated raw data, membrane prediction map (CebraNET), supervoxel map, and segmentation maps can be viewed using the MoBIE viewer (39).…”

Section: Resultsmentioning

confidence: 99%

“…The big-dataviewer-based MoBIE viewer (39) was used to inspect large datasets. MoBIE enables image pyramid-based lazy loading of the data and scales to arbitrary data size.…”

Section: Data Visualization and Data Storagementioning

confidence: 99%

“…To visualize and browse full EM datasets including membrane prediction, supervoxel maps, and segmentations, we used the MoBIE viewer (39). A CebraEM project is an extension of a Mo-BIE project such that it can be loaded directly into the viewer where each desired volume can be selected for visualization and segmentations or supervoxels can be viewed as an overlay over the respective EM data volume or membrane prediction map.…”

Section: Data Visualization and 3d Renderingmentioning

confidence: 99%

See 3 more Smart Citations

CebraEM: A practical workflow to segment cellular organelles in volume SEM datasets using a transferable CNN-based membrane prediction

Hennies

Lleti

Pape

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Segmentation of large-volume datasets obtained by volume SEM techniques is a challenging task that generally requires a considerable amount of human effort. Despite recent advances in deep learning leading to the successful segmentation of cellular organelles in a variety of datasets, it is still challenging and time-consuming to produce the necessary data for training a convolutional neural network as well as to set up targeted post-processing pipelines to obtain a good quality full-volume semantic instance segmentation. We present CebraEM, a software package that uses a novel workflow for the segmentation of organelles in volume EM datasets, which helps to minimize the annotation time for the generation of training data. It relies on a generic CNN-based membrane prediction, followed by a well-established machine-learning pipeline that includes over-segmentation before random forest classification and graph multi-cut grouping. The workflow was tested for the segmentation of organelles on different datasets originating from various sample preparations and imaging modalities in volume SEM, in each case resulting in state-of-the-art semantic instance segmentations without additional post-processing. Importantly, by considerably simplifying the segmentation problem, CebraEM empowers single users with the ability to efficiently segment hundreds of gigabytes of data.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

“…The big-dataviewer-based MoBIE viewer (39) was used to inspect large datasets. MoBIE enables image pyramid-based lazy loading of the data and scales to arbitrary data size.…”

Section: Data Visualization and Data Storagementioning

confidence: 99%

Section: Data Visualization and 3d Renderingmentioning

confidence: 99%

See 2 more Smart Citations

CebraEM: A practical workflow to segment cellular organelles in volume SEM datasets using a transferable CNN-based membrane prediction

Hennies

Lleti

Pape

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This has previously been dealt with by converting into either tiff stacks or raw volumes to enable data exchange. Newer file formats such as hdf5 66 or OME-NGFF 67 as implemented by OME-ZARR 68 , may facilitate easier transfer of the raw data and associated metadata between sites, using software such as MoBie 69 . Other options for sharing the data online such as webknossos 70 , which was designed for 3DEM images, or Horos cloud (Horos, https://horosproject.org/ ).…”

Section: Discussionmentioning

confidence: 99%

A high-throughput 3D X-ray histology facility for biomedical research and preclinical applications

Katsamenis,

Basford,

Robinson

et al. 2023

Wellcome Open Res

View full text Add to dashboard Cite

Background The University of Southampton, in collaboration with the University Hospital Southampton (UHS) NHS Foundation Trust and industrial partners, has been at the forefront of developing three-dimensional (3D) imaging workflows using X-ray microfocus computed tomography (μCT) -based technology. This article presents the outcomes of these endeavours and highlights the distinctive characteristics of a μCT facility tailored explicitly for 3D X-ray Histology, with a primary focus on applications in biomedical research and preclinical and clinical studies. Methods The UHS houses a unique 3D X-ray Histology (XRH) facility, offering a range of services to national and international clients. The facility employs specialised μCT equipment explicitly designed for histology applications, allowing whole-block XRH imaging of formalin-fixed and paraffin-embedded tissue specimens. It also enables correlative imaging by combining μCT imaging with other microscopy techniques, such as immunohistochemistry (IHC) and serial block-face scanning electron microscopy, as well as data visualisation, image quantification, and bespoke analysis. Results Over the past seven years, the XRH facility has successfully completed over 120 projects in collaboration with researchers from 60 affiliations, resulting in numerous published manuscripts and conference proceedings. The facility has streamlined the μCT imaging process, improving productivity and enabling efficient acquisition of 3D datasets. Discussion & Conclusions The 3D X-ray Histology (XRH) facility at UHS is a pioneering platform in the field of histology and biomedical imaging. To the best of our knowledge, it stands out as the world's first dedicated XRH facility, encompassing every aspect of the imaging process, from user support to data generation, analysis, training, archiving, and metadata generation. This article serves as a comprehensive guide for establishing similar XRH facilities, covering key aspects of facility setup and operation. Researchers and institutions interested in developing state-of-the-art histology and imaging facilities can utilise this resource to explore new frontiers in their research and discoveries.

show abstract

Toward scalable reuse of vEM data: OME-Zarr to the rescue

Rzepka¹,

Bogovic²,

Moore³

2023

Volume Electron Microscopy

View full text Add to dashboard Cite

MoBIE: a Fiji plugin for sharing and exploration of multi-modal cloud-hosted big image data

Cited by 11 publications

References 10 publications

CebraEM: A practical workflow to segment cellular organelles in volume SEM datasets using a transferable CNN-based membrane prediction

CebraEM: A practical workflow to segment cellular organelles in volume SEM datasets using a transferable CNN-based membrane prediction

A high-throughput 3D X-ray histology facility for biomedical research and preclinical applications

Toward scalable reuse of vEM data: OME-Zarr to the rescue

Contact Info

Product

Resources

About