scispace - formally typeset
Open accessJournal ArticleDOI: 10.1371/JOURNAL.PCBI.1008374

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

02 Mar 2021-PLOS Computational Biology (Public Library of Science (PLoS))-Vol. 17, Iss: 3
Abstract: We present DeepMIB, a new software package that is capable of training convolutional neural networks for segmentation of multidimensional microscopy datasets on any workstation. We demonstrate its successful application for segmentation of 2D and 3D electron and multicolor light microscopy datasets with isotropic and anisotropic voxels. We distribute DeepMIB as both an open-source multi-platform Matlab code and as compiled standalone application for Windows, MacOS and Linux. It comes in a single package that is simple to install and use as it does not require knowledge of programming. DeepMIB is suitable for everyone interested of bringing a power of deep learning into own image segmentation workflows.

... read more

Topics: Image segmentation (60%), Deep learning (53%), Software (53%) ... show more
Citations
  More

6 results found


Open accessJournal ArticleDOI: 10.1038/S41467-021-22518-0
Abstract: Deep Learning (DL) methods are powerful analytical tools for microscopy and can outperform conventional image processing pipelines. Despite the enthusiasm and innovations fuelled by DL technology, the need to access powerful and compatible resources to train DL networks leads to an accessibility barrier that novice users often find difficult to overcome. Here, we present ZeroCostDL4Mic, an entry-level platform simplifying DL access by leveraging the free, cloud-based computational resources of Google Colab. ZeroCostDL4Mic allows researchers with no coding expertise to train and apply key DL networks to perform tasks including segmentation (using U-Net and StarDist), object detection (using YOLOv2), denoising (using CARE and Noise2Void), super-resolution microscopy (using Deep-STORM), and image-to-image translation (using Label-free prediction - fnet, pix2pix and CycleGAN). Importantly, we provide suitable quantitative tools for each network to evaluate model performance, allowing model optimisation. We demonstrate the application of the platform to study multiple biological processes.

... read more

Topics: Deep learning (51%)

45 Citations


Open accessJournal ArticleDOI: 10.1038/S41592-021-01284-3
01 Oct 2021-Nature Methods
Abstract: Deep 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.

... read more

Topics: Transformative learning (51%)

4 Citations


Open accessPosted Content
Abstract: The living body is composed of innumerable fine and complex structures and although these structures have been studied in the past, a vast amount of information pertaining to them still remains unknown. When attempting to observe these ultra-structures, the use of electron microscopy (EM) has become indispensable. However, conventional EM settings are limited to a narrow tissue area that can bias observations. Recently, new trends in EM research have emerged that provide coverage of far broader, nano-scale fields of view for two-dimensional wide areas and three-dimensional large volumes. Together with cutting-edge bioimage informatics conducted via deep learning, such techniques have accelerated the quantification of complex morphological images. Moreover, these advances have led to the comprehensive acquisition and quantification of cellular morphology, which is now treated as a new omics science termed 'morphomics'. Moreover, by incorporating these new methodologies, the field of traditional pathology is expected to advance, potentially with the identification of previously unknown structures, quantification of rare events, reclassification of diseases and automatic diagnosis of diseases. In this review, we discuss these technological and analytical advances, which have arisen from the need to analyse nano-scale bioimages, in detail, as well as focusing on state-of-art image analysis involving deep learning.

... read more

Topics: Bioimage informatics (52%)

Open accessJournal ArticleDOI: 10.1111/JMI.13056
Abstract: Correlative light and electron microscopy is a valuable tool to image samples across resolution scales and link data on structure and function. While studies using this technique have been available since the 1960s, recent developments have enabled applying these workflows to large volumes of cells and tissues. Much of the development in this area has been facilitated through the collaborative efforts of microscopists and commercial companies to bring the methods, hardware and image processing technologies needed into laboratories and core imaging facilities. This is a prime example of how what was once a niche area can be brought into the mainstream of microscopy by the efforts of imaging pioneers who push the boundaries of possibility.

... read more


Open accessPosted Content
Abstract: 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 96.6% 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 ~31k epithelium annotations are made openly available at this https URL to accelerate research in the field.

... read more

Topics: Digital pathology (51%)

References
  More

24 results found


Open accessBook ChapterDOI: 10.1007/978-3-319-24574-4_28
05 Oct 2015-
Abstract: There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net .

... read more

Topics: Brain segmentation (57%), Deep learning (54%), Segmentation (50%)

28,273 Citations


Open accessJournal ArticleDOI: 10.1109/TPAMI.2016.2644615
Abstract: We present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine consists of an encoder network, a corresponding decoder network followed by a pixel-wise classification layer. The architecture of the encoder network is topologically identical to the 13 convolutional layers in the VGG16 network [1] . The role of the decoder network is to map the low resolution encoder feature maps to full input resolution feature maps for pixel-wise classification. The novelty of SegNet lies is in the manner in which the decoder upsamples its lower resolution input feature map(s). Specifically, the decoder uses pooling indices computed in the max-pooling step of the corresponding encoder to perform non-linear upsampling. This eliminates the need for learning to upsample. The upsampled maps are sparse and are then convolved with trainable filters to produce dense feature maps. We compare our proposed architecture with the widely adopted FCN [2] and also with the well known DeepLab-LargeFOV [3] , DeconvNet [4] architectures. This comparison reveals the memory versus accuracy trade-off involved in achieving good segmentation performance. SegNet was primarily motivated by scene understanding applications. Hence, it is designed to be efficient both in terms of memory and computational time during inference. It is also significantly smaller in the number of trainable parameters than other competing architectures and can be trained end-to-end using stochastic gradient descent. We also performed a controlled benchmark of SegNet and other architectures on both road scenes and SUN RGB-D indoor scene segmentation tasks. These quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures. We also provide a Caffe implementation of SegNet and a web demo at http://mi.eng.cam.ac.uk/projects/segnet/ .

... read more

Topics: Encoder (54%), Convolutional neural network (53%), Image segmentation (53%) ... show more

8,450 Citations


Proceedings ArticleDOI: 10.1109/ICDAR.2003.1227801
03 Aug 2003-
Abstract: Neural networks are a powerful technology forclassification of visual inputs arising from documents.However, there is a confusing plethora of different neuralnetwork methods that are used in the literature and inindustry. This paper describes a set of concrete bestpractices that document analysis researchers can use toget good results with neural networks. The mostimportant practice is getting a training set as large aspossible: we expand the training set by adding a newform of distorted data. The next most important practiceis that convolutional neural networks are better suited forvisual document tasks than fully connected networks. Wepropose that a simple "do-it-yourself" implementation ofconvolution with a flexible architecture is suitable formany visual document problems. This simpleconvolutional neural network does not require complexmethods, such as momentum, weight decay, structure-dependentlearning rates, averaging layers, tangent prop,or even finely-tuning the architecture. The end result is avery simple yet general architecture which can yieldstate-of-the-art performance for document analysis. Weillustrate our claims on the MNIST set of English digitimages.

... read more

2,443 Citations


Journal ArticleDOI: 10.1038/S41593-018-0209-Y
Alexander Mathis1, Pranav Mamidanna1, Kevin M. Cury2, Taiga Abe2  +4 moreInstitutions (3)
Abstract: Quantifying behavior is crucial for many applications in neuroscience. Videography provides easy methods for the observation and recording of animal behavior in diverse settings, yet extracting particular aspects of a behavior for further analysis can be highly time consuming. In motor control studies, humans or other animals are often marked with reflective markers to assist with computer-based tracking, but markers are intrusive, and the number and location of the markers must be determined a priori. Here we present an efficient method for markerless pose estimation based on transfer learning with deep neural networks that achieves excellent results with minimal training data. We demonstrate the versatility of this framework by tracking various body parts in multiple species across a broad collection of behaviors. Remarkably, even when only a small number of frames are labeled (~200), the algorithm achieves excellent tracking performance on test frames that is comparable to human accuracy.

... read more

Topics: Pose (53%)

1,057 Citations


Open accessJournal ArticleDOI: 10.1371/JOURNAL.PBIO.2005970
03 Jul 2018-PLOS Biology
Abstract: CellProfiler has enabled the scientific research community to create flexible, modular image analysis pipelines since its release in 2005. Here, we describe CellProfiler 3.0, a new version of the software supporting both whole-volume and plane-wise analysis of three-dimensional (3D) image stacks, increasingly common in biomedical research. CellProfiler's infrastructure is greatly improved, and we provide a protocol for cloud-based, large-scale image processing. New plugins enable running pretrained deep learning models on images. Designed by and for biologists, CellProfiler equips researchers with powerful computational tools via a well-documented user interface, empowering biologists in all fields to create quantitative, reproducible image analysis workflows.

... read more

850 Citations


Performance
Metrics
No. of citations received by the Paper in previous years
YearCitations
20216
Network Information
Related Papers (5)
Interactive 3-D segmentation22 Sep 1992

Thomas Schiemann, M. Bomans +2 more

74% related
Interseg: a distributed image segmentation tool14 Sep 2016

P. N. Happ, Rodrigo S. Ferreira +5 more

72% related
Labkit: Labeling and Segmentation Toolkit for Big Image Data15 Oct 2021, bioRxiv

Matthias Arzt, Joran Deschamps +7 more

71% related
A framework and user interface for automatic region based segmentation algorithms01 Dec 2006

Kevin McGuinness, Gordon Keenan +2 more

70% related