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

Belevich, Ilya; Jokitalo, Eija

doi:10.1371/journal.pcbi.1008374

Cited by 53 publications

(31 citation statements)

References 24 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…U-Net is a fully-convolutional encoder-decoder neural network initially developed for the purpose of biomedical image segmentation. U-Net is one of two available 2D semantic segmentation networks in DeepMIB which allows optimization of hyperparameters such as U-Net depth, number of filters and input patch size for each segmentation task (16). SegNet is a fully-convolutional encoderdecoder neural network where the encoder part is identical to the 13 convolutional layers in the much-used VGG16 network (19).…”

Section: U-net Based Epithelial Segmentation Using Qupath and Deepmibmentioning

confidence: 99%

“…The typical deep learning workflows require knowledge of deep learning architectures, Python programming abilities, and general experience with multiple software installations. The code-free solution DeepMIB was published to help with all these aspects and with a hope to make deep learning available to a wider community of biological researchers (16). DeepMIB is a userfriendly software package that was designed to provide a smooth experience for training of convolutional neural networks (CNN) for segmentation of light and electron microscopy datasets.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology

et al. 2022

Self Cite

View full text Add to dashboard Cite

Application of deep learning on histopathological whole slide images (WSIs) holds promise of improving diagnostic efficiency and reproducibility but is largely dependent on the ability to write computer code or purchase commercial solutions. We present a code-free pipeline utilizing free-to-use, open-source software (QuPath, DeepMIB, and FastPathology) for creating and deploying deep learning-based segmentation models for computational pathology. We demonstrate the pipeline on a use case of separating epithelium from stroma in colonic mucosa. A dataset of 251 annotated WSIs, comprising 140 hematoxylin-eosin (HE)-stained and 111 CD3 immunostained colon biopsy WSIs, were developed through active learning using the pipeline. On a hold-out test set of 36 HE and 21 CD3-stained WSIs a mean intersection over union score of 95.5 and 95.3% was achieved on epithelium segmentation. We demonstrate pathologist-level segmentation accuracy and clinical acceptable runtime performance and show that pathologists without programming experience can create near state-of-the-art segmentation solutions for histopathological WSIs using only free-to-use software. The study further demonstrates the strength of open-source solutions in its ability to create generalizable, open pipelines, of which trained models and predictions can seamlessly be exported in open formats and thereby used in external solutions. All scripts, trained models, a video tutorial, and the full dataset of 251 WSIs with ~31 k epithelium annotations are made openly available at https://github.com/andreped/NoCodeSeg to accelerate research in the field.

show abstract

Section: U-net Based Epithelial Segmentation Using Qupath and Deepmibmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…First, we recommend choosing a well-documented and well-maintained tool that matches the user's preferred interface. Available DL tools now span various web interfaces 27,32 , standalone software 22,26,32,44 , plugins for popular image analysis software 10,11,25,45 , online notebooks 20 and Python packages 46 . Each platform requires a different level of technical skill to use.…”

Section: Choosing a DL Toolmentioning

confidence: 99%

“…In comparison, using DL models (predictions) can be straightforward (parameter-free one-click solutions) and fast (seconds to minutes) even on a local machine. Multiple tools are in development to facilitate the training and use of DL for bioimage analysis, including both online and offline, commercial and open-source solutions 8,[20][21][22][23][24][25][26][27][28] . Choosing the most appropriate tool out of these options largely depends on what tasks or combination of tasks need to be performed, the scale of the analysis and the level of computational skills required to run them.…”

mentioning

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

“…In addition to ImageJ, several other image analysis software packages include plug-ins for deep learning. DeepMIB ( Belevich and Jokitalo, 2021 ) is a deep-learning–based image segmentation plug-in for two- and three-dimensional data sets bundled with the Microscopy Image Browser (MIB), an open-source MATLAB-based image analysis application for light microscopy and electron microscopy. Users can load data sets, test pretrained models or train a model via a graphical user interface (GUI).…”

Section: Deep-learning Plug-ins For Popular Image Analysis Toolboxesmentioning

confidence: 99%

Open-source deep-learning software for bioimage segmentation

Lucas

Ryder

et al. 2021

MBoC

View full text Add to dashboard Cite

Microscopy images are rich in information about the dynamic relationships among biological structures. However, extracting this complex information can be challenging, especially when biological structures are closely packed, distinguished by texture rather than intensity, and/or low intensity relative to the background. By learning from large amounts of annotated data, deep learning can accomplish several previously intractable bioimage analysis tasks. Until the past few years, however, most deep-learning workflows required significant computational expertise to be applied. Here, we survey several new open-source software tools that aim to make deep-learning–based image segmentation accessible to biologists with limited computational experience. These tools take many different forms, such as web apps, plug-ins for existing imaging analysis software, and preconfigured interactive notebooks and pipelines. In addition to surveying these tools, we overview several challenges that remain in the field. We hope to expand awareness of the powerful deep-learning tools available to biologists for image analysis.

show abstract

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

Cited by 53 publications

References 24 publications

Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology

Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology

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

Open-source deep-learning software for bioimage segmentation

Contact Info

Product

Resources

About