DeepMIB: User-friendly and open-source software for training of deep learning network for biological image segmentation

Belevich, Ilya; Jokitalo, Eija

doi:10.1101/2020.07.13.200105

Cited by 4 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, most user-friendly tools delegate the training step to method developers and implement prediction with pretrained models for end users. These tools include DeepImageJ 179 , the ilastik neural network workflow 164 , DeepMIB 180 , CDeep3M 181 , epanada 182 and APEER (Zeiss). For successful application, the model needs to be trained on data very similar to the data at hand, preferably using generalizability-enhancing tricks such as data augmentation, while unsupervised pretraining on large unlabelled and heterogeneous datasets may increase model performance overall 183 .…”

Section: Resultsmentioning

confidence: 99%

Volume electron microscopy

Peddie

Genoud

Kreshuk

et al. 2022

Nat Rev Methods Primers

103

View full text Add to dashboard Cite

Life exists in three dimensions, but until the turn of the century most electron microscopy methods provided only 2D image data. Recently, electron microscopy techniques capable of delving deep into the structure of cells and tissues have emerged, collectively called volume electron microscopy (vEM). Developments in vEM have been dubbed a quiet revolution as the field evolved from established transmission and scanning electron microscopy techniques, so early publications largely focused on the bioscience applications rather than the underlying technological breakthroughs. However, with an explosion in the uptake of vEM across the biosciences and fast-paced advances in volume, resolution, throughput and ease of use, it is timely to introduce the field to new audiences. In this Primer, we introduce the different vEM imaging modalities, the specialized sample processing and image analysis pipelines that accompany each modality and the types of information revealed in the data. We showcase key applications in the biosciences where vEM has helped make breakthrough discoveries and consider limitations and future directions. We aim to show new users how vEM can support discovery science in their own research fields and inspire broader uptake of the technology, finally allowing its full adoption into mainstream biological imaging.

show abstract

Section: Resultsmentioning

confidence: 99%

Volume electron microscopy

Peddie

Genoud

Kreshuk

et al. 2022

Nat Rev Methods Primers

103

View full text Add to dashboard Cite

show abstract

“…The cell boundaries were segmented semi-automatically using the Graphcut tool of MIB, while the Golgi stacks were manually identified and segmented using the Brush tool aided by interpolation technique to fill the gaps between slices with the drawn profiles. All nuclei (except one crypt segmented with the Graphcut tool) were segmented using 2D DeepLabV3-Resnet50 69 convolutional neural network trained and applied in DeepMIB 70 . The final model of nuclei was generated by multi-view fusion, when 2D predictions from sagittal, coronal, and axial planes are fused together.…”

Section: Methodsmentioning

confidence: 99%

Golgi organization is a determinant of stem cell function in the small intestine

Scharaw

Sola-Carvajal

Belevich

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Cell-to-cell signalling between niche and stem cells regulates tissue regeneration. While the identity of many mediating factors is known, it is largely unknown whether stem cells optimize their receptiveness to niche signals according to the niche organization. Here, we show that Lgr5+ small intestinal stem cells (ISCs) regulate the morphology and orientation of their secretory apparatus to match the niche architecture, and to increase transport efficiency of niche signal receptors. Unlike the progenitor cells lacking lateral niche contacts, ISCs orient Golgi apparatus laterally towards Paneth cells of the epithelial niche, and divide Golgi into multiple stacks reflecting the number of Paneth cell contacts. Stem cells with a higher number of lateral Golgi transported Epidermal growth factor receptor (Egfr) with a higher efficiency than cells with one Golgi. The lateral Golgi orientation and enhanced Egfr transport required A-kinase anchor protein 9 (Akap9), and was necessary for normal regenerative capacity in vitro. Moreover, reduced Akap9 in aged ISCs renders ISCs insensitive to niche-dependent modulation of Golgi stack number and transport efficiency. Our results reveal stem cell-specific Golgi complex configuration that facilitates efficient niche signal reception and tissue regeneration, which is compromised in the aged epithelium.

show abstract

“…First, we recommend choosing an active, well-documented and well-maintained tool that matches the user’s prefered interface. Available DL tools now span various web interfaces 29 , 32 , standalone software 24 , 28 , 32 , 41 , plugins for popular image analysis software 10 , 11 , 27 , 42 , online notebooks 22 and Python packages 43 . Each platform requires a different level of technical skills to use.…”

Section: Choosing a DL Toolmentioning

confidence: 99%

Avoiding a replication crisis in deep-learning-based bioimage analysis

et al. 2021

View full text Add to dashboard Cite

Avoiding a replication crisis in deep-learningbased bioimage analysisDeep learning algorithms are powerful tools for analyzing, restoring and transforming bioimaging data. One promise of deep learning is parameter-free one-click image analysis with expert-level performance in a fraction of the time previously required. However, as with most emerging technologies, the potential for inappropriate use is raising concerns among the research community. In this comment, we discuss key concepts that we believe are important for researchers to consider when using deep learning for their microscopy studies. We describe how results obtained using deep learning can be validated and propose what should, in our view, be considered when choosing a suitable tool. We also suggest what aspects of a deep learning analysis should be reported in publications to ensure reproducibility. We hope this perspective will foster further discussion among developers, image analysis specialists, users and journal editors to define adequate guidelines and ensure the appropriate use of this transformative technology.

show abstract

DeepMIB: User-friendly and open-source software for training of deep learning network for biological image segmentation

Cited by 4 publications

References 24 publications

Volume electron microscopy

Volume electron microscopy

Golgi organization is a determinant of stem cell function in the small intestine

Avoiding a replication crisis in deep-learning-based bioimage analysis

Contact Info

Product

Resources

About