Automated Training of Deep Convolutional Neural Networks for Cell Segmentation

Sadanandan, Sajith Kecheril; Ranefall, Petter; Guyader, Sylvie Le; Wählby, Carolina

doi:10.1038/s41598-017-07599-6

Cited by 126 publications

(97 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Long et al, 2010) applied DL methods to unlabeled and unsegmented images of low-density cultures with mixtures of three cell types and trained a network to classify cell types. (Sadanandan et al, 2017) used DL to segment cells from brightfield z -stacks, and also showed that cell nuclei can be segmented from non-nuclei fluorescent markers. Unfortunately, the task of predicting fluorescence images from transmitted light images is not well served by typical classification models such as Inception (Szegedy et al, 2015a) because they typically contain spatial reductions that destroy fine detail.…”

Section: Discussionmentioning

confidence: 99%

In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images

Christiansen

Yang

Ando

et al. 2018

Cell

563

465

View full text Add to dashboard Cite

Microscopy is a central method in life sciences. Many popular methods, such as antibody labeling, are used to add physical fluorescent labels to specific cellular constituents. However, these approaches have significant drawbacks, including inconsistency; limitations in the number of simultaneous labels because of spectral overlap; and necessary perturbations of the experiment, such as fixing the cells, to generate the measurement. Here, we show that a computational machine-learning approach, which we call "in silico labeling" (ISL), reliably predicts some fluorescent labels from transmitted-light images of unlabeled fixed or live biological samples. ISL predicts a range of labels, such as those for nuclei, cell type (e.g., neural), and cell state (e.g., cell death). Because prediction happens in silico, the method is consistent, is not limited by spectral overlap, and does not disturb the experiment. ISL generates biological measurements that would otherwise be problematic or impossible to acquire.

show abstract

Section: Discussionmentioning

confidence: 99%

In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images

Christiansen

Yang

Ando

et al. 2018

Cell

563

465

View full text Add to dashboard Cite

show abstract

“…However, trypsin digestion also provide important practical advantages because disaggregated cells can be more evenly dispersed in a microscopy well-plate, which improves the robustness of the segmentation process. Previous studies to discriminate cells based on imaging required seeding cells on a surface, where segmentation is more complex and cell-surface interactions can influence cell morphology [26][27][28] . Disaggregated cell samples provide a simpler, more rapid, and more uniform imaging condition.…”

Section: Discussionmentioning

confidence: 99%

Image-based Cell Phenotyping Using Deep Learning

Berryman

Matthews

Lee

et al. 2019

Preprint

View full text Add to dashboard Cite

The ability to phenotype cells is fundamentally important in biological research and medicine. Current methods rely primarily on fluorescence labeling of specific markers. However, there are many situations where this approach is unavailable or undesirable. Machine learning has been used for image cytometry but has been limited by cell agglomeration and it is unclear if this approach can reliably phenotype cells indistinguishable to the human eye. Here, we show disaggregated single cells can be phenotyped with a high degree of accuracy using low-resolution bright-field and non-specific fluorescence images of the nucleus, cytoplasm, and cytoskeleton. Specifically, we trained a convolutional neural network using automatically segmented images of cells from eight standard cancer cell-lines. These cells could be identified with an average classification accuracy of 94.6%, tested using separately acquired images. Our results demonstrate the potential to develop an "electronic eye" to phenotype cells directly from microscopy images indistinguishable to the human eye.Image Based Cell Phenotyping Using Deep-Learning

show abstract

“…In recent years, computational advances in deep convolutional neural-networks (CNNs) have produced models that match, and sometimes exceed, human levels of performance in a variety of classification, clustering, and segmentation tasks in biological image analysis (4)(5)(6). More specifically, several studies have described novel CNN-based approaches for the segmentation of nuclei from fluorescence microscopy images (7)(8)(9)(10)(11)(12)(13).…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Pipeline for Nucleus Segmentation

Zaki

Gudla

Lee

et al. 2020

Preprint

View full text Add to dashboard Cite

Deep learning is rapidly becoming the technique of choice for automated segmentation of nuclei in biological image analysis workflows. In order to improve and understand the training parameters that drive the performance of deep learning models trained on small, custom annotated image datasets, we have designed a computational pipeline to systematically test different nuclear segmentation model architectures and model training strategies. Using this approach, we demonstrate that transfer learning and tuning of training parameters, such as the training image dataset composition, size and pre-processing, can lead to robust nuclear segmentation models, which match, and often exceed, the performance of existing, state-of-the-art deep learning models pre-trained on large image datasets. Our work provides computational tools and a practical framework for the improvement of deep learning-based biological image segmentation using small annotated image datasets.

show abstract

Automated Training of Deep Convolutional Neural Networks for Cell Segmentation

Cited by 126 publications

References 13 publications

In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images

In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images

Image-based Cell Phenotyping Using Deep Learning

A Deep Learning Pipeline for Nucleus Segmentation

Contact Info

Product

Resources

About